© 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. 14039
    Prev
    Next
    INDEX
    Explanations

    template-related code snippets

    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
    57
    +0.12
    0.5%
    247
    +0.11
    0.4%
    321
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.04
    604
    +0.11
    0.03
    57
    +0.10
    0.03
    Negative Logits
    akers
    -1.04
    apolis
    -0.98
    atures
    -0.95
    oys
    -0.93
    aker
    -0.89
    atur
    -0.88
     Cann
    -0.84
    aten
    -0.81
    atin
    -0.79
     Peaks
    -0.79
    POSITIVE LOGITS
    cffffcc
    0.90
    {{
    0.85
    Ŀ
    0.75
     wik
    0.73
    draft
    0.72
    hemy
    0.72
     booking
    0.72
    netflix
    0.72
     grep
    0.71
     username
    0.70
    Activations Density 0.409%

    No Known Activations