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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 24428
    Prev
    Next
    INDEX
    Explanations

    text related to file management or data transfer

    oai_token-act-pair · gpt-3.5-turbo

    sections related to technical specifications or data

    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
    holders
    -0.67
    ãĢIJ
    -0.60
    icipated
    -0.59
    rov
    -0.58
    gradation
    -0.58
    ichever
    -0.57
    etermination
    -0.56
    bye
    -0.56
    finding
    -0.56
    Bey
    -0.55
    POSITIVE LOGITS
     KB
    0.78
     Mehran
    0.73
     dstg
    0.69
     Lod
    0.61
     Sherman
    0.60
    cript
    0.59
     Paste
    0.59
     partName
    0.58
     Unloaded
    0.58
     Whedon
    0.56
    Activations Density 0.021%

    No Known Activations