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. 6-RES-JB
    6. 23049
    Prev
    Next
    INDEX
    Explanations

    sports-related terms, particularly associated with a team named "Sporting"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Sporting" and "VS" in the context of competitive events or teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ered
    -0.93
    er
    -0.86
    ebook
    -0.85
    ed
    -0.84
    erer
    -0.80
    Reviewer
    -0.79
    edded
    -0.77
    ewater
    -0.76
    rosse
    -0.76
    cake
    -0.74
    POSITIVE LOGITS
    ignty
    0.86
    PsyNetMessage
    0.85
    terday
    0.80
    sembly
    0.76
    idency
    0.76
    apons
    0.74
    ipes
    0.71
    ocial
    0.69
    olutions
    0.68
    ync
    0.68
    Activations Density 0.075%

    No Known Activations