© 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. 36891
    Prev
    Next
    INDEX
    Explanations

    technical information related to electricity, circuits, and data formats

    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
    +0.25
    1.0%
    311
    +0.15
    0.6%
    514
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.25
    0.26
    283
    +0.15
    0.02
    173
    +0.13
    0.09
    Negative Logits
    ItemImage
    -0.81
     conduc
    -0.80
    ercise
    -0.79
    £ı
    -0.70
    lov
    -0.68
    akov
    -0.68
    lehem
    -0.66
    cerning
    -0.65
    jet
    -0.65
    perty
    -0.64
    POSITIVE LOGITS
    xff
    1.47
    xd
    1.13
    xe
    1.10
    xc
    1.10
    x
    1.10
    xb
    1.05
    xa
    1.04
    603
    0.99
    644
    0.95
    ½
    0.94
    Activations Density 13.336%

    No Known Activations