© 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. 45700
    Prev
    Next
    INDEX
    Explanations

    days of the week

    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
    +0.21
    1.0%
    649
    +0.15
    0.7%
    651
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.21
    0.08
    274
    +0.15
    0.10
    239
    +0.14
    0.09
    Negative Logits
    acus
    -0.93
    emort
    -0.86
    emale
    -0.82
    inav
    -0.78
    anooga
    -0.73
    ethical
    -0.72
    icidal
    -0.72
    umbn
    -0.71
    itars
    -0.70
    icide
    -0.70
    POSITIVE LOGITS
    pring
    1.00
    dream
    0.97
    days
    0.92
     ago
    0.90
    ilver
    0.82
    trip
    0.81
    DAY
    0.79
    hops
    0.75
    care
    0.74
    hift
    0.74
    Activations Density 11.434%

    No Known Activations