© 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. 4680
    Prev
    Next
    INDEX
    Explanations

    articles, news updates, and technical information

    oai_token-act-pair · gpt-3.5-turbo

    references to media content and additional information sources

    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
    etheless
    -0.59
     fault
    -0.59
    eln
    -0.57
     interfered
    -0.56
    ©¶æ¥µ
    -0.55
    SpaceEngineers
    -0.55
     lasted
    -0.54
     nurs
    -0.54
     exacerbated
    -0.53
    Prev
    -0.53
    POSITIVE LOGITS
     please
    1.47
    please
    1.24
     click
    1.24
     CLICK
    1.21
     PLEASE
    1.16
     check
    1.13
     visit
    1.02
     consult
    0.99
     see
    0.99
     consider
    0.97
    Activations Density 0.244%

    No Known Activations