© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 14786
    Prev
    Next
    INDEX
    Explanations

    code-related phrases and expressions

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding errors or issues related to assignment in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.86
    surprisingly
    -0.67
    xtap
    -0.67
    uitive
    -0.66
    wcs
    -0.62
    theless
    -0.59
     respondents
    -0.59
    minist
    -0.57
    prisingly
    -0.57
    ciplinary
    -0.56
    POSITIVE LOGITS
    .")
    1.75
    ").
    1.72
    ")
    1.69
    )",
    1.69
    "]
    1.66
    "),
    1.63
     ..."
    1.61
    )"
    1.58
    !",
    1.52
    ");
    1.50
    Activations Density 1.021%

    No Known Activations