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. 2-RES-JB
    6. 9674
    Prev
    Next
    INDEX
    Explanations

    names of a specific individual, likely "Malkin"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Malkin" and associated references in the context of a sports discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĸ¬âĸ¬
    -0.88
    ciples
    -0.80
    versely
    -0.71
    ciating
    -0.71
    ching
    -0.70
    pled
    -0.70
    >>>>>>>>
    -0.69
    fts
    -0.68
    Lay
    -0.67
    cess
    -0.67
    POSITIVE LOGITS
     Morg
    0.95
    sburgh
    0.93
     Malk
    0.85
    essel
    0.81
    itol
    0.81
    bard
    0.80
    atform
    0.78
    heim
    0.78
    utenberg
    0.75
    hattan
    0.75
    Activations Density 0.025%

    No Known Activations