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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 21134
    Prev
    Next
    INDEX
    Explanations

    dates expressed in numbers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number six in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.72
    romeda
    -0.64
     Seym
    -0.57
    tainment
    -0.55
    Reviewer
    -0.55
    plom
    -0.55
    terday
    -0.54
    atem
    -0.52
    etheless
    -0.52
    llor
    -0.52
    POSITIVE LOGITS
    ½
    0.82
    th
    0.82
    teenth
    0.72
    eenth
    0.70
    %"
    0.69
     ½
    0.69
    °
    0.68
    ecause
    0.67
    %-
    0.65
    %,
    0.64
    Activations Density 0.444%

    No Known Activations