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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 4718
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals or organizations, presumably named "Cord"

    oai_token-act-pair · gpt-3.5-turbo

    references to entities or concepts associated with "Cord."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kin
    -0.66
    QUIRE
    -0.64
    kins
    -0.63
    ting
    -0.62
    kens
    -0.61
    spect
    -0.61
    ij士
    -0.57
    kered
    -0.57
    advertising
    -0.57
    GL
    -0.57
    POSITIVE LOGITS
    inates
    1.23
    inated
    1.15
    inator
    1.11
    ova
    1.10
    elia
    1.05
    nance
    1.04
    ially
    1.04
    inately
    1.02
    inators
    1.02
    inances
    1.02
    Activations Density 0.068%

    No Known Activations