© 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. 3747
    Prev
    Next
    INDEX
    Explanations

    words related to storytelling and interactions between characters in a script

    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
    640
    +0.38
    1.5%
    539
    +0.16
    0.6%
    721
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.38
    0.21
    64
    +0.16
    -0.06
    649
    +0.15
    0.08
    Negative Logits
     inactive
    -0.97
     blinded
    -0.95
    obar
    -0.92
     estranged
    -0.86
    oval
    -0.86
    llor
    -0.85
     worthless
    -0.85
     indisc
    -0.82
     retali
    -0.82
     punitive
    -0.81
    POSITIVE LOGITS
    Newsletter
    1.09
    Anyway
    1.05
    ONSORED
    0.99
    RAY
    0.95
    Wa
    0.94
    Certainly
    0.92
     Anyway
    0.92
    Were
    0.91
    ³³³³³³³³³³³³³³³³
    0.90
    Rail
    0.89
    Activations Density 1.178%

    No Known Activations