© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 14663
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to violence or conflict

    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
    308
    +0.15
    0.5%
    529
    +0.14
    0.5%
    420
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.15
    0.04
    420
    +0.14
    0.04
    529
    +0.14
    0.04
    Negative Logits
    icum
    -1.17
    oresc
    -1.11
    ord
    -1.08
    idious
    -1.01
    flies
    -0.99
    ulhu
    -0.97
    onds
    -0.96
    odi
    -0.96
    ixel
    -0.94
    othal
    -0.92
    POSITIVE LOGITS
    â̦â̦â̦â̦â̦â̦â̦â̦
    1.40
    â̦â̦â̦â̦
    1.39
    ////////////////////////////////
    1.07
    ³³³³³³³³³³³³³³³³
    1.03
    âĢ¢âĢ¢âĢ¢âĢ¢
    1.03
    BUT
    0.98
     Continue
    0.97
     Written
    0.95
    ³³³³³³³³
    0.90
     Appears
    0.90
    Activations Density 0.620%

    No Known Activations