© 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 EvalsExportsinterp-engineNEWAPI 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. 35362
    Prev
    Next
    INDEX
    Explanations

    information related to statistics and research findings, especially pertaining to education and migration trends

    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
    +0.27
    1.0%
    260
    +0.13
    0.5%
    173
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    693
    +0.27
    0.13
    260
    +0.13
    0.13
    173
    +0.12
    0.09
    Negative Logits
    merce
    -0.86
    plin
    -0.82
     satell
    -0.79
    ĵĺ
    -0.75
    izzle
    -0.72
    ilater
    -0.70
    isites
    -0.68
     guiName
    -0.68
    arak
    -0.67
    shoot
    -0.67
    POSITIVE LOGITS
    %)
    1.69
    %),
    1.54
    +)
    1.52
    )=
    1.42
    )
    1.35
    ),"
    1.34
    )/
    1.33
    %).
    1.32
    )</
    1.27
    ),
    1.24
    Activations Density 9.220%

    No Known Activations