© 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. 9-RES-JB
    11. 15407
    Prev
    Next
    INDEX
    Explanations

    mentions of specific entities or topics

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of a specific placeholder or identifier in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.72
     Canaver
    -0.70
    gew
    -0.69
     Gould
    -0.68
    vor
    -0.68
    vim
    -0.68
    ribly
    -0.68
    rolet
    -0.65
    ties
    -0.63
    athed
    -0.62
    POSITIVE LOGITS
     responders
    1.10
     Published
    1.01
     baseman
    0.87
     impressions
    0.83
     lady
    0.82
     Nations
    0.82
     Appearance
    0.81
     ancest
    0.81
     timers
    0.79
    Lady
    0.75
    Activations Density 0.060%

    No Known Activations