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. 10-RES-JB
    6. 13441
    Prev
    Next
    INDEX
    Explanations

    comments or discussions related to a specific topic or matter

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating discussion or analysis of significant topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Such
    -0.73
     thereof
    -0.73
     thereto
    -0.71
    They
    -0.70
    advertisement
    -0.70
    "}],"
    -0.70
    These
    -0.68
    isans
    -0.66
    tis
    -0.65
    "},{"
    -0.64
    POSITIVE LOGITS
     alot
    0.71
     Luffy
    0.66
     GHC
    0.65
     my
    0.60
     EVERY
    0.60
     everything
    0.60
     our
    0.59
     the
    0.58
     Dumbledore
    0.55
     Marshal
    0.55
    Activations Density 0.801%

    No Known Activations