© 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. 34760
    Prev
    Next
    INDEX
    Explanations

    objects and actions related to ropes and tying

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    598
    +0.13
    0.6%
    225
    +0.11
    0.5%
    447
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.23
    526
    +0.11
    -0.07
    225
    +0.11
    0.09
    Negative Logits
    ONSORED
    -0.79
     Atmosp
    -0.78
    estate
    -0.78
    renheit
    -0.77
    auder
    -0.74
     Scotia
    -0.73
    aturday
    -0.69
    amins
    -0.67
    issance
    -0.67
    vironments
    -0.66
    POSITIVE LOGITS
     ropes
    1.08
     leash
    1.05
     knot
    1.05
     rope
    1.03
    tie
    1.02
     securely
    1.01
     tightly
    0.97
     knots
    0.96
     harness
    0.95
    binding
    0.90
    Activations Density 10.140%

    No Known Activations