© 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. 10-RES-JB
    11. 1289
    Prev
    Next
    INDEX
    Explanations

    references to signing up for newsletters or subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to newsletters and subscription services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesota
    -0.69
    76561
    -0.67
    wich
    -0.62
    liest
    -0.62
    lihood
    -0.60
    rior
    -0.56
     FIG
    -0.55
    Footnote
    -0.53
    vable
    -0.53
     JUSTICE
    -0.53
    POSITIVE LOGITS
    glas
    0.70
    daily
    0.69
    ylon
    0.69
    selves
    0.67
    Amazing
    0.66
    news
    0.64
    ernaut
    0.64
    blogs
    0.64
    eli
    0.63
    ridges
    0.61
    Activations Density 0.033%

    No Known Activations