© 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. 39646
    Prev
    Next
    INDEX
    Explanations

    information related to wildlife health and diseases, particularly in the context of bats

    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
    447
    +0.17
    0.8%
    497
    +0.12
    0.6%
    390
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    381
    +0.17
    0.12
    289
    +0.12
    -0.04
    35
    +0.10
    0.07
    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.81
     ministry
    -0.72
     reincarn
    -0.70
     logistics
    -0.67
     Dispatch
    -0.64
     careers
    -0.63
     schedules
    -0.63
     classics
    -0.62
     relevance
    -0.60
     timetable
    -0.60
    POSITIVE LOGITS
     protr
    0.96
     diameter
    0.85
     formed
    0.82
     forming
    0.82
    icles
    0.82
     pores
    0.79
     ooz
    0.78
     beneath
    0.76
     thickness
    0.76
     indent
    0.75
    Activations Density 16.045%

    No Known Activations