© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5683
    Prev
    Next
    INDEX
    Explanations

    words related to food ingredients and culinary practices, with a focus on coriander seeds

    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
    326
    +0.15
    0.7%
    461
    +0.11
    0.5%
    563
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.15
    0.11
    481
    +0.11
    0.14
    563
    +0.10
    0.11
    Negative Logits
    ©¶æ¥µ
    -0.82
    ãģ¾
    -0.71
    ãĥ©ãĥ³
    -0.67
    establishment
    -0.65
     ..."
    -0.63
    Fla
    -0.63
    «ĺ
    -0.62
    )",
    -0.62
    specified
    -0.60
    ãģĻ
    -0.60
    POSITIVE LOGITS
     behaves
    0.84
     also
    0.82
     operates
    0.80
     exists
    0.78
     is
    0.77
     performs
    0.76
     reminds
    0.76
     employs
    0.74
     fared
    0.74
     consists
    0.74
    Activations Density 2.423%

    No Known Activations