© 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. 5281
    Prev
    Next
    INDEX
    Explanations

    phrases indicating allowing or accepting something to happen or to continue

    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
    393
    +0.14
    0.5%
    261
    +0.13
    0.5%
    639
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    560
    +0.14
    0.04
    237
    +0.13
    0.04
    261
    +0.13
    0.03
    Negative Logits
    enegger
    -1.24
     Archdemon
    -0.94
     Slug
    -0.92
    senal
    -0.91
     Maul
    -0.88
    ccording
    -0.87
    ModLoader
    -0.84
    atl
    -0.83
     Annotations
    -0.83
    ELD
    -0.81
    POSITIVE LOGITS
     shine
    0.97
     breathe
    0.95
     loose
    0.90
     slip
    0.88
    rete
    0.86
     free
    0.85
     freely
    0.82
     happen
    0.80
     escape
    0.80
    erella
    0.80
    Activations Density 0.725%

    No Known Activations