© 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. 1416
    Prev
    Next
    INDEX
    Explanations

    references to video game development and specific game features

    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
    288
    +0.17
    0.6%
    336
    +0.14
    0.5%
    167
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    698
    +0.17
    0.06
    197
    +0.14
    0.06
    651
    +0.13
    0.06
    Negative Logits
    orescent
    -0.98
     politic
    -0.94
    inx
    -0.93
    thens
    -0.91
    thening
    -0.91
    ayers
    -0.89
    ignt
    -0.86
    olulu
    -0.81
    sie
    -0.80
    cellaneous
    -0.75
    POSITIVE LOGITS
    wright
    1.45
    pad
    1.31
    cube
    1.18
    PLAY
    1.13
    manship
    1.06
     Borderlands
    1.04
     consoles
    1.03
    play
    1.03
    plays
    1.02
    Maker
    1.01
    Activations Density 0.605%

    No Known Activations