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. 9-RES-JB
    6. 131
    Prev
    Next
    INDEX
    Explanations

    proper nouns representing entities with a superlative status or size

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "largest" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    skirts
    -0.78
    lik
    -0.77
    fen
    -0.77
    facing
    -0.76
    docs
    -0.73
    instead
    -0.73
    ious
    -0.72
    ses
    -0.71
    ills
    -0.70
    yang
    -0.69
    POSITIVE LOGITS
     shareholder
    0.92
    gest
    0.91
     (>
    0.87
     swath
    0.86
     chunk
    0.83
     proponent
    0.81
     seller
    0.81
     amount
    0.80
     denomination
    0.80
     purchaser
    0.79
    Activations Density 0.028%

    No Known Activations