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

    Neuronpedia

    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. 14200
    Prev
    Next
    INDEX
    Explanations

    phrases related to social justice movements or political actions

    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
    283
    +0.17
    0.5%
    183
    +0.15
    0.5%
    651
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.17
    0.04
    274
    +0.15
    0.05
    183
    +0.15
    0.05
    Negative Logits
    issance
    -1.15
    aud
    -1.00
    ilee
    -0.97
     Taste
    -0.92
    æѦ
    -0.90
    ancing
    -0.88
    ible
    -0.87
    ï¸
    -0.86
    ishable
    -0.86
    Jay
    -0.86
    POSITIVE LOGITS
    tle
    1.58
     forth
    1.51
    ters
    1.31
    tering
    1.29
    rid
    1.26
     aside
    1.25
     sail
    1.20
    ter
    1.19
    offs
    1.19
    itud
    1.08
    Activations Density 0.883%

    No Known Activations