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. 17294
    Prev
    Next
    INDEX
    Explanations

    phrases related to arithmetic and calculations

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of totaling or summing up information

    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
    anus
    -0.77
    jah
    -0.75
    ni
    -0.73
    oway
    -0.68
    GN
    -0.66
    Anne
    -0.64
    avage
    -0.64
    hal
    -0.64
    ow
    -0.64
    gow
    -0.63
    POSITIVE LOGITS
     probabilities
    0.79
     discrepancies
    0.72
    tten
    0.71
    grading
    0.71
     inconsistencies
    0.70
     totals
    0.70
     irregularities
    0.69
    MpServer
    0.69
    skirts
    0.68
     successes
    0.68
    Activations Density 0.026%

    No Known Activations