© 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
    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. 13674
    Prev
    Next
    INDEX
    Explanations

    words related to continuation or advancement from a previous point

    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
    207
    +0.12
    0.5%
    356
    +0.12
    0.5%
    160
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    187
    +0.12
    0.03
    504
    +0.12
    0.02
    543
    +0.12
    0.02
    Negative Logits
     caps
    -0.81
    orie
    -0.77
    oret
    -0.73
     Hurricanes
    -0.72
    ivable
    -0.72
    dan
    -0.68
     Bean
    -0.68
    idia
    -0.68
     Dome
    -0.67
     capture
    -0.66
    POSITIVE LOGITS
    jriwal
    0.89
    ©¶æ
    0.78
    stairs
    0.77
    Marx
    0.77
    ###
    0.77
     misunder
    0.76
    sterdam
    0.75
    à¼
    0.74
    appa
    0.74
    âĸł
    0.74
    Activations Density 0.096%

    No Known Activations