© 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. 1878
    Prev
    Next
    INDEX
    Explanations

    recipes and cooking instructions, with a particular focus on ingredients and preparation steps

    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
    7
    +0.18
    0.6%
    214
    +0.17
    0.6%
    709
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.18
    0.10
    288
    +0.17
    0.11
    709
    +0.16
    0.08
    Negative Logits
    CHR
    -1.00
    resy
    -0.95
     predator
    -0.95
    omorph
    -0.94
     gobl
    -0.93
     carniv
    -0.90
    APH
    -0.89
     Cage
    -0.89
    ocene
    -0.87
    artifacts
    -0.87
    POSITIVE LOGITS
    ioned
    1.45
    ington
    1.45
    IELD
    1.42
    ield
    1.37
    ing
    1.29
    edIn
    1.19
    ressing
    1.17
    resses
    1.17
    ucket
    1.16
    iling
    1.10
    Activations Density 1.738%

    No Known Activations