© 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. 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. 3432
    Prev
    Next
    INDEX
    Explanations

    news headlines indicating further details are available

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "Read more" indicating additional content or links

    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
     Reborn
    -0.67
     ILCS
    -0.63
    OHN
    -0.62
    intend
    -0.61
     FIG
    -0.59
    xon
    -0.58
     Clown
    -0.57
    oled
    -0.55
     KING
    -0.55
    poon
    -0.55
    POSITIVE LOGITS
    iness
    0.63
     defence
    0.62
     More
    0.59
    arching
    0.56
     fue
    0.55
     organising
    0.55
    htaking
    0.54
    ners
    0.54
    iesta
    0.53
    Write
    0.52
    Activations Density 0.021%

    No Known Activations