© 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. 1344
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals, organizations, or places

    oai_token-act-pair · gpt-3.5-turbo

    references to the United States or discussions revolving around American contexts

    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
    rought
    -0.68
    ottest
    -0.64
    ITNESS
    -0.62
    ynasty
    -0.62
    estine
    -0.60
    itness
    -0.60
    tons
    -0.59
    sie
    -0.58
    issance
    -0.57
     td
    -0.57
    POSITIVE LOGITS
    pex
    1.17
    peed
    1.12
    CRIP
    1.11
    sein
    1.10
    chwitz
    1.08
    cular
    1.06
    pect
    1.01
    etts
    0.98
    cules
    0.94
    aurus
    0.92
    Activations Density 0.083%

    No Known Activations