© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 21082
    Prev
    Next
    INDEX
    Explanations

    years represented by four-number combinations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of dates or years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plom
    -0.67
    ittal
    -0.66
    £ı
    -0.66
    ettings
    -0.65
    ño
    -0.64
    abolic
    -0.64
    afort
    -0.63
    ochet
    -0.62
    luster
    -0.61
     waning
    -0.60
    POSITIVE LOGITS
    âĸĪâĸĪ
    1.12
    th
    1.07
    committee
    1.05
    40
    1.04
    48
    0.99
    %
    0.96
    61
    0.94
    26
    0.93
    52
    0.92
    28
    0.91
    Activations Density 0.093%

    No Known Activations