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. 3-RES-JB
    6. 14841
    Prev
    Next
    INDEX
    Explanations

    names with the pattern "Dob" and "Hodgson"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those with the surname "Dob" or "Hodg."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.86
    inventoryQuantity
    -0.83
    izational
    -0.72
     Titanic
    -0.70
    TPS
    -0.69
    WAYS
    -0.68
     ILCS
    -0.68
    Advertisements
    -0.64
    xual
    -0.64
    ãĤĤ
    -0.64
    POSITIVE LOGITS
    sonian
    1.31
    rolet
    1.09
     Dob
    1.09
    bing
    1.05
    rov
    1.02
    achev
    0.95
    bs
    0.94
    zik
    0.92
    anium
    0.92
    itsch
    0.91
    Activations Density 0.004%

    No Known Activations