© 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. 2-RES-JB
    6. 23466
    Prev
    Next
    INDEX
    Explanations

    references to the word "number"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "number" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ellen
    -0.68
     Gutenberg
    -0.66
    selection
    -0.61
     observable
    -0.61
    ogene
    -0.61
    DNA
    -0.59
    kef
    -0.57
     Franken
    -0.57
     segregated
    -0.56
     Stories
    -0.56
    POSITIVE LOGITS
    umber
    0.97
    umbers
    0.82
    batch
    0.80
    jack
    0.79
    parts
    0.79
    é¾įåĸļ士
    0.77
    deen
    0.77
    maid
    0.76
    cake
    0.76
    yard
    0.74
    Activations Density 0.006%

    No Known Activations