© 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. 37012
    Prev
    Next
    INDEX
    Explanations

    information related to authors and contributors in text

    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
    167
    +0.11
    0.6%
    339
    +0.11
    0.6%
    688
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.11
    0.07
    683
    +0.11
    0.07
    472
    +0.11
    0.05
    Negative Logits
    ttes
    -0.74
    roads
    -0.61
    ll
    -0.58
     Bottle
    -0.56
     Peb
    -0.56
     retard
    -0.55
    romy
    -0.54
    enegger
    -0.53
    eyes
    -0.53
    tto
    -0.53
    POSITIVE LOGITS
    itative
    1.22
    itarian
    1.02
    itatively
    0.93
    ity
    0.90
    izations
    0.88
    itized
    0.81
    izes
    0.79
    isation
    0.77
    iversary
    0.76
    ised
    0.75
    Activations Density 5.454%

    No Known Activations