© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12457
    Prev
    Next
    INDEX
    Explanations

    sentiments related to political opinions and attitudes, particularly regarding controversial topics like policy decisions and public figures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    442
    +0.16
    0.6%
    749
    +0.13
    0.5%
    455
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    456
    +0.16
    0.05
    661
    +0.13
    0.04
    742
    +0.12
    0.05
    Negative Logits
    zbollah
    -0.98
     Byz
    -0.97
    mone
    -0.90
     Renaissance
    -0.89
     garg
    -0.89
     laure
    -0.88
    Redd
    -0.86
     distribut
    -0.85
     Gutenberg
    -0.84
     accomp
    -0.84
    POSITIVE LOGITS
     respondents
    1.07
     polled
    0.97
    een
    0.96
     surveyed
    0.93
    ril
    0.90
     percent
    0.89
    osuke
    0.88
    percent
    0.87
    pc
    0.86
    IU
    0.86
    Activations Density 0.381%

    No Known Activations