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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16449
    Prev
    Next
    INDEX
    Explanations

    the term "undisputed" or "disputing", suggesting a sense of clear agreement or disagreement

    oai_token-act-pair · gpt-3.5-turbo
    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
     cass
    -0.69
     caps
    -0.67
     disarm
    -0.65
     ment
    -0.63
     trips
    -0.63
     gravy
    -0.63
     Graham
    -0.63
     upl
    -0.62
     sabotage
    -0.62
     scarf
    -0.62
    POSITIVE LOGITS
    puted
    4.61
    putable
    2.01
    puting
    1.59
     computed
    1.24
    parable
    1.09
    put
    0.99
    PUT
    0.97
    plete
    0.96
    pleted
    0.95
    ferred
    0.93
    Activations Density 0.028%

    No Known Activations