© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31399
    Prev
    Next
    INDEX
    Explanations

    phrases related to training programs and educational activities

    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
    1.1%
    288
    +0.16
    0.7%
    575
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.23
    0.29
    362
    +0.16
    0.15
    385
    +0.15
    0.17
    Negative Logits
    osi
    -0.81
    vous
    -0.72
    izon
    -0.70
    ventory
    -0.68
    portation
    -0.66
    atos
    -0.65
    ogene
    -0.65
    peria
    -0.64
    aceae
    -0.64
    itous
    -0.64
    POSITIVE LOGITS
     Peaks
    0.95
     manuals
    0.80
     seminars
    0.79
     sessions
    0.79
     exercises
    0.77
     acad
    0.76
    UFC
    0.76
     camps
    0.74
     academy
    0.73
     wheels
    0.72
    Activations Density 13.392%

    No Known Activations