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

    Neuronpedia

    Jacobian LensNEW
    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. 33263
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to data analysis and medical analysis 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
    447
    +0.28
    1.3%
    393
    +0.15
    0.7%
    620
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.28
    0.12
    362
    +0.15
    0.11
    614
    +0.12
    0.05
    Negative Logits
    chenko
    -0.73
    ivil
    -0.71
    reat
    -0.70
    qqa
    -0.70
    Russ
    -0.66
    beat
    -0.65
    å£
    -0.65
    illin
    -0.65
    edin
    -0.64
    mare
    -0.64
    POSITIVE LOGITS
     purposes
    1.13
    gery
    1.08
     example
    1.07
     instance
    1.03
    bidden
    1.01
     determining
    1.00
     sake
    0.98
    geries
    0.95
     starters
    0.94
     comparison
    0.94
    Activations Density 8.669%

    No Known Activations