© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 10056
    Prev
    Next
    INDEX
    Explanations

    complex and thought-provoking questions or issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases that raise questions or issues related to ethics and morality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.74
    ĪĴ
    -0.74
    cknow
    -0.64
    ãĥ¼ãĥĨãĤ£
    -0.59
     finished
    -0.57
     disbanded
    -0.57
    urated
    -0.56
     repealed
    -0.56
    installed
    -0.55
    anish
    -0.55
    POSITIVE LOGITS
     for
    0.93
     regarding
    0.88
     concerning
    0.84
    FOR
    0.76
     about
    0.76
     beyond
    0.75
    undrum
    0.73
    .","
    0.72
    about
    0.68
     FOR
    0.68
    Activations Density 0.288%

    No Known Activations