© 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. 11016
    Prev
    Next
    INDEX
    Explanations

    dates and events related to legal actions

    oai_token-act-pair · gpt-3.5-turbo

    files and metadata associated with images or documents

    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
    76561
    -0.71
    ========
    -0.68
    ============
    -0.66
    talk
    -0.62
    lihood
    -0.62
    Reviewer
    -0.61
    Party
    -0.58
    abol
    -0.57
    =~
    -0.57
    ãĥİ
    -0.56
    POSITIVE LOGITS
     photo
    1.03
     illustration
    1.01
     FILE
    0.97
     photograph
    0.96
     screenshot
    0.91
    FILE
    0.90
     portrait
    0.86
     file
    0.86
    window
    0.80
    file
    0.77
    Activations Density 0.069%

    No Known Activations