Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 2993
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal documents or organizational processes

    oai_token-act-pair · gpt-3.5-turbo

    references to Freedom of Information (FOI) requests and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assian
    -0.74
     Rothschild
    -0.68
    atchewan
    -0.67
    interstitial
    -0.65
    udeau
    -0.64
    ifying
    -0.62
    ansas
    -0.61
    naire
    -0.60
     McKin
    -0.60
     praying
    -0.59
    POSITIVE LOGITS
    LLOW
    1.22
     FO
    1.20
    ILS
    0.96
    OSE
    0.90
    rodu
    0.89
    ¥µ
    0.87
    ZZ
    0.87
    IRE
    0.85
    IL
    0.84
    ĪĴ
    0.84
    Activations Density 0.005%

    No Known Activations