© 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. 9-RES-JB
    11. 16025
    Prev
    Next
    INDEX
    Explanations

    social media platform mentions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media platforms

    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
     Proced
    -0.62
    uilding
    -0.60
    pit
    -0.59
     Fusion
    -0.58
     stewards
    -0.58
    lav
    -0.58
    uberty
    -0.58
    ĪĴ
    -0.58
     Reborn
    -0.58
     retrospective
    -0.57
    POSITIVE LOGITS
     SHARES
    0.96
     Flavoring
    0.87
    ÙĦ
    0.71
     Whats
    0.67
     WRITE
    0.64
     NET
    0.60
    LIN
    0.59
    à¼
    0.59
     Shares
    0.58
    orie
    0.58
    Activations Density 0.023%

    No Known Activations