© 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. 36857
    Prev
    Next
    INDEX
    Explanations

    numeric data such as measurements, percentages, and prices

    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
    +0.20
    0.8%
    640
    +0.16
    0.7%
    393
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.20
    0.06
    640
    +0.16
    0.14
    250
    +0.13
    0.05
    Negative Logits
     advis
    -0.82
     totality
    -0.74
     swim
    -0.73
     handshake
    -0.73
     sentimental
    -0.73
     recre
    -0.71
    iqueness
    -0.70
     attacker
    -0.69
     ownership
    -0.68
     continuum
    -0.68
    POSITIVE LOGITS
    5
    1.45
    9
    1.39
    99
    1.38
    95
    1.36
    8
    1.35
    75
    1.30
    6
    1.29
    7
    1.27
    25
    1.27
    0
    1.25
    Activations Density 5.726%

    No Known Activations