© 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. 37120
    Prev
    Next
    INDEX
    Explanations

    numerals, dates and technical information

    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
    447
    +0.22
    0.9%
    326
    +0.16
    0.6%
    302
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.22
    0.43
    447
    +0.16
    0.45
    64
    +0.13
    -0.18
    Negative Logits
    aye
    -0.95
    aeus
    -0.95
    rd
    -0.94
    achu
    -0.91
    reek
    -0.87
    aith
    -0.86
    eners
    -0.85
    rous
    -0.85
    eton
    -0.84
    ened
    -0.81
    POSITIVE LOGITS
    20439
    1.17
    384
    0.87
    6666
    0.87
    0100
    0.85
    554
    0.85
    557
    0.82
    tenance
    0.80
    315
    0.79
    chester
    0.79
    MHz
    0.78
    Activations Density 8.764%

    No Known Activations