© 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. 33808
    Prev
    Next
    INDEX
    Explanations

    keywords related to news articles

    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
    496
    +0.11
    0.6%
    167
    +0.11
    0.6%
    326
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    748
    +0.11
    0.05
    740
    +0.11
    0.09
    68
    +0.08
    0.04
    Negative Logits
    angers
    -0.62
    phy
    -0.55
    phies
    -0.55
    bows
    -0.55
    amel
    -0.54
    perties
    -0.54
    phi
    -0.54
     Springer
    -0.53
    grass
    -0.52
    graded
    -0.52
    POSITIVE LOGITS
     ALSO
    0.90
     MORE
    0.87
    ING
    0.84
    INGS
    0.81
    LESS
    0.77
    ME
    0.74
    BOOK
    0.74
    LIN
    0.74
    MORE
    0.72
     TRAN
    0.71
    Activations Density 6.466%

    No Known Activations