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. 7-RES-JB
    6. 16938
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms that are often capitalized

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "BA."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atures
    -0.77
    omen
    -0.77
    ittal
    -0.73
    ivities
    -0.72
    strip
    -0.71
    serious
    -0.68
    ively
    -0.68
    espie
    -0.66
    ivity
    -0.66
    ostics
    -0.66
    POSITIVE LOGITS
    BIP
    1.16
    wark
    0.86
    keley
    0.84
    uble
    0.84
    ñ
    0.81
    asketball
    0.79
    BILITIES
    0.78
    EGIN
    0.77
    iting
    0.77
     fide
    0.77
    Activations Density 0.019%

    No Known Activations