© 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. 2-RES-JB
    11. 965
    Prev
    Next
    INDEX
    Explanations

    the word "number"

    oai_token-act-pair · gpt-4-turbo

    numbers indicating quantity or magnitude

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "number" in various contexts

    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
    rador
    -0.81
    Interstitial
    -0.75
    sbm
    -0.73
    INTON
    -0.71
    Accessory
    -0.68
    aimon
    -0.68
    clair
    -0.67
    interstitial
    -0.66
    Materials
    -0.64
    aples
    -0.64
    POSITIVE LOGITS
     number
    0.90
    number
    0.85
     numbers
    0.79
    ########
    0.73
     Numbers
    0.72
     digits
    0.71
    encies
    0.69
    atur
    0.68
    ones
    0.68
     tens
    0.66
    Activations Density 0.036%

    No Known Activations