© 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. 31219
    Prev
    Next
    INDEX
    Explanations

    names and locations

    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
    +0.19
    0.8%
    710
    +0.13
    0.5%
    16
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.19
    0.10
    167
    +0.13
    -0.02
    670
    +0.11
    0.08
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -1.12
    ividual
    -1.05
    ãĥ¼ãĥĨ
    -1.04
    etheless
    -1.03
    aneers
    -0.99
    ãģĨ
    -0.98
    âĶģ
    -0.90
    raints
    -0.84
    iaries
    -0.82
     teasp
    -0.81
    POSITIVE LOGITS
    isure
    1.39
    lean
    1.22
    icester
    1.15
    ukemia
    1.13
    opard
    1.11
    agues
    1.08
    ather
    1.02
    aching
    1.00
    utenant
    0.97
    ven
    0.96
    Activations Density 7.900%

    No Known Activations