© 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. 3645
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols commonly used in coding, potentially related to a specific programming language or system

    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
    655
    +0.16
    0.5%
    146
    +0.15
    0.5%
    699
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.16
    0.17
    392
    +0.15
    0.12
    639
    +0.14
    0.10
    Negative Logits
    soDeliveryDate
    -1.04
    kok
    -0.96
    Priv
    -0.94
    hole
    -0.93
    ĪĴ
    -0.93
    wcs
    -0.89
    zona
    -0.88
     captcha
    -0.87
     methodological
    -0.85
    ĸļ
    -0.85
    POSITIVE LOGITS
    ruary
    1.90
    tein
    1.26
    illet
    1.01
    heit
    1.01
    ascript
    1.01
    owship
    0.97
    gerald
    0.97
    oppers
    0.96
     sake
    0.95
    igure
    0.95
    Activations Density 5.330%

    No Known Activations