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. 10-RES-JB
    6. 9026
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals and locations

    oai_token-act-pair · gpt-3.5-turbo

    names or terms associated with individuals and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulators
    -0.79
    fram
    -0.78
    sburgh
    -0.75
    inventoryQuantity
    -0.73
    itudes
    -0.71
    ulatory
    -0.69
    ocene
    -0.68
    ãģĻ
    -0.68
    âĸĪâĸĪ
    -0.67
    ][/
    -0.66
    POSITIVE LOGITS
    hyde
    0.84
    ynamic
    0.81
    cember
    0.75
    rolet
    0.75
    ynam
    0.73
     Mub
    0.73
    backs
    0.72
    ennes
    0.70
    VID
    0.69
    onna
    0.66
    Activations Density 0.240%

    No Known Activations