© 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. 31332
    Prev
    Next
    INDEX
    Explanations

    references to specific time periods, particularly focusing on events happening at night

    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
    +0.18
    0.9%
    748
    +0.11
    0.5%
    430
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.18
    0.09
    589
    +0.11
    0.08
    504
    +0.10
    0.08
    Negative Logits
    berman
    -0.72
    krit
    -0.61
    ocide
    -0.59
     Galile
    -0.58
    mental
    -0.56
    verbs
    -0.56
    lasses
    -0.55
    eer
    -0.55
    insured
    -0.54
    ipl
    -0.54
    POSITIVE LOGITS
     afternoon
    0.90
     evening
    0.86
     tonight
    0.83
     Tonight
    0.81
     Evening
    0.81
     night
    0.70
     morning
    0.70
    Tonight
    0.69
     Hots
    0.69
    night
    0.69
    Activations Density 7.417%

    No Known Activations