© 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. 3608
    Prev
    Next
    INDEX
    Explanations

    instances of argumentative language and discussion of controversial topics

    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
    393
    +0.15
    0.5%
    68
    +0.14
    0.5%
    147
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    333
    +0.15
    0.08
    45
    +0.14
    0.06
    151
    +0.14
    0.11
    Negative Logits
    utenberg
    -1.04
    ocene
    -1.03
    usterity
    -1.02
    igger
    -0.98
    eni
    -0.94
    monton
    -0.89
    igers
    -0.89
    resa
    -0.85
    rieve
    -0.85
    atre
    -0.84
    POSITIVE LOGITS
     thereafter
    1.39
     consequently
    1.33
     expects
    1.12
    etheless
    1.06
     invests
    1.05
     proceeded
    1.04
     conclud
    1.03
     importantly
    1.03
     secondly
    1.03
     integrates
    1.01
    Activations Density 2.981%

    No Known Activations