© 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. 36295
    Prev
    Next
    INDEX
    Explanations

    instances where the content discusses environmental or societal issues and potential solutions

    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
    +0.23
    1.5%
    640
    +0.09
    0.6%
    509
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.23
    0.40
    6
    +0.09
    0.29
    255
    +0.08
    0.21
    Negative Logits
    tein
    -0.45
     booze
    -0.42
     cradle
    -0.41
    ensibly
    -0.41
    pan
    -0.41
    ä¸Ń
    -0.40
    Neal
    -0.39
    jah
    -0.39
    tin
    -0.39
    resa
    -0.38
    POSITIVE LOGITS
     etc
    0.76
    etc
    0.60
     alike
    0.53
     thereof
    0.52
     respectively
    0.49
    endif
    0.49
     IMAGES
    0.48
    uyomi
    0.48
    ockets
    0.47
    depending
    0.47
    Activations Density 17.613%

    No Known Activations