© 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. 35594
    Prev
    Next
    INDEX
    Explanations

    phrases related to scenes of change, development, and transformation

    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
    +0.14
    0.6%
    393
    +0.11
    0.5%
    185
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    132
    +0.14
    0.11
    43
    +0.11
    0.08
    351
    +0.10
    0.05
    Negative Logits
    oru
    -0.63
     Balls
    -0.62
    ister
    -0.62
    ainer
    -0.60
    Ö¼
    -0.59
    Motion
    -0.59
     Cutter
    -0.59
    atown
    -0.58
     respondent
    -0.57
    arium
    -0.57
    POSITIVE LOGITS
    aire
    0.79
     hoops
    0.79
    nut
    0.79
     hoop
    0.76
     fuss
    0.72
    undy
    0.71
     facets
    0.71
    together
    0.71
    eties
    0.71
    nuts
    0.71
    Activations Density 8.815%

    No Known Activations