Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 0-RES-JB
    6. 14226
    Prev
    Next
    INDEX
    Explanations

    instances of the word "exclamation"

    oai_token-act-pair · gpt-3.5-turbo

    exclamatory phrases and associated claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     len
    -0.66
     Strauss
    -0.66
     biased
    -0.65
     Dir
    -0.64
     bias
    -0.63
     Wolfgang
    -0.62
     ske
    -0.61
     setups
    -0.61
     Russ
    -0.60
     ii
    -0.60
    POSITIVE LOGITS
    clamation
    4.37
    claim
    1.34
    claimed
    1.33
    posal
    1.05
    orbit
    0.99
    plet
    0.97
    pection
    0.97
    reci
    0.95
    inventoryQuantity
    0.93
    claimer
    0.93
    Activations Density 0.030%

    No Known Activations