© 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 EvalsExportsAPI 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. 33720
    Prev
    Next
    INDEX
    Explanations

    instances where the word "for" is followed by a mix of numbers and letters, such as "FOR9" or "FOR7CE1"

    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
    +0.19
    0.8%
    641
    +0.12
    0.5%
    314
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.19
    -0.00
    152
    +0.12
    0.16
    641
    +0.11
    0.13
    Negative Logits
    inese
    -0.66
     jaws
    -0.66
    adelphia
    -0.62
     vom
    -0.57
    zona
    -0.57
     Ples
    -0.56
    omi
    -0.55
    Tube
    -0.55
    marine
    -0.54
     tailor
    -0.54
    POSITIVE LOGITS
    gotten
    1.64
    bidden
    1.53
     example
    1.12
    WARD
    1.10
     instance
    1.08
    gery
    1.04
    cing
    1.03
    ged
    0.98
    cible
    0.96
    ced
    0.95
    Activations Density 8.189%

    No Known Activations