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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 19113
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is excessive or extreme

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express limitations or conditions that are "too" extreme

    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
     largeDownload
    -0.77
    escal
    -0.72
    ãĤ¢ãĥ«
    -0.71
    kind
    -0.71
    ãĥĨ
    -0.65
    ãĤ¼
    -0.65
    iste
    -0.64
    ãĥ©ãĥ³
    -0.64
    TPP
    -0.63
    written
    -0.62
    POSITIVE LOGITS
     anymore
    0.77
     warrant
    0.73
     foreseeable
    0.71
     adequately
    0.71
     anything
    0.71
     feas
    0.71
     Spoon
    0.68
    rists
    0.68
     necessarily
    0.66
     qualify
    0.65
    Activations Density 0.069%

    No Known Activations