© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 35577
    Prev
    Next
    INDEX
    Explanations

    mentions of specific subsections or titles

    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
    232
    +0.18
    0.7%
    167
    +0.12
    0.5%
    59
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    667
    +0.18
    0.08
    649
    +0.12
    0.04
    214
    +0.11
    0.05
    Negative Logits
     Cors
    -0.89
    OHN
    -0.88
     Papers
    -0.86
    20439
    -0.83
    INESS
    -0.82
    çİĭ
    -0.82
     fir
    -0.82
     Zurich
    -0.81
    DERR
    -0.80
     Dol
    -0.80
    POSITIVE LOGITS
    mitted
    1.78
    sequent
    1.75
    sequently
    1.66
    stantial
    1.59
    mitting
    1.44
    ordinate
    1.43
    marine
    1.42
    scription
    1.40
    lime
    1.34
    stant
    1.33
    Activations Density 5.650%

    No Known Activations