Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 905
    Prev
    Next
    INDEX
    Explanations

    emails

    oai_token-act-pair · gpt-3.5-turbo

    words or parts of words containing the sequence "an"

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    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
    343
    +0.04
    0.4%
    311
    +0.04
    0.4%
    635
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    61
    +0.04
    0.02
    70
    +0.04
    0.02
    737
    +0.04
    0.02
    Negative Logits
     Rebell
    -0.32
     legends
    -0.29
    querque
    -0.29
    displayText
    -0.27
    grave
    -0.25
    utenberg
    -0.25
    Þ
    -0.25
    ĨĴ
    -0.24
     vacancies
    -0.23
     legend
    -0.23
    POSITIVE LOGITS
    cgi
    0.32
    etheless
    0.29
    allo
    0.27
    boat
    0.26
    erest
    0.26
    ity
    0.26
    yip
    0.25
    Ott
    0.25
    atana
    0.24
    xiety
    0.24
    Activations Density 0.132%

    No Known Activations