© 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 Local
    9. 6-RES_SCL-AJT
    11. 40831
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and laboratory procedures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    585
    +0.10
    0.4%
    362
    +0.10
    0.4%
    656
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.10
    0.01
    326
    +0.10
    0.24
    678
    +0.10
    0.08
    Negative Logits
    estate
    -0.99
    hello
    -0.80
    NetMessage
    -0.79
     Sovere
    -0.79
    terday
    -0.78
    emale
    -0.76
    abouts
    -0.76
    uality
    -0.75
    incent
    -0.75
    ussie
    -0.75
    POSITIVE LOGITS
     PCR
    1.19
     assay
    1.18
     situ
    0.97
     cyt
    0.96
     PowerPoint
    0.94
     ±
    0.90
     nm
    0.90
     phot
    0.87
     intraven
    0.87
     ml
    0.84
    Activations Density 11.314%

    No Known Activations