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. 8-RES-JB
    6. 5696
    Prev
    Next
    INDEX
    Explanations

    references to objects or entities related to the word "Pan"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Pan," likely related to the Pan American context or associated events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itability
    -0.64
     minded
    -0.63
     confir
    -0.62
    enance
    -0.61
     Judd
    -0.61
     Gilmore
    -0.61
    IELD
    -0.60
     guiIcon
    -0.59
    ãĤī
    -0.59
     Yankee
    -0.59
    POSITIVE LOGITS
    orama
    1.27
    acea
    1.12
    tera
    1.10
    zers
    1.06
    alyst
    1.00
    etta
    0.97
    ahon
    0.97
    omaly
    0.95
    asonic
    0.94
    amera
    0.92
    Activations Density 0.030%

    No Known Activations