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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14066
    Prev
    Next
    INDEX
    Explanations

    long phrases or specific word patterns

    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
    240
    +0.15
    0.5%
    584
    +0.14
    0.5%
    435
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    493
    +0.15
    0.05
    303
    +0.14
    0.04
    435
    +0.12
    0.03
    Negative Logits
    encer
    -1.13
     livest
    -1.10
    è¦ļéĨĴ
    -1.02
    yrinth
    -1.02
    iasco
    -1.00
    cffff
    -1.00
    iners
    -1.00
    aughs
    -0.99
     prosec
    -0.99
    ilings
    -0.96
    POSITIVE LOGITS
    fare
    1.75
    ward
    1.64
    point
    1.39
    WARD
    1.37
    finding
    1.35
    points
    1.33
    bill
    1.25
    yy
    1.17
    stones
    1.12
    YY
    1.10
    Activations Density 0.735%

    No Known Activations