© 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. 7-RES-JB
    11. 11792
    Prev
    Next
    INDEX
    Explanations

    numerical references to amounts or quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities in hundreds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obal
    -0.71
     Indust
    -0.64
    udic
    -0.62
    hra
    -0.62
    HAM
    -0.61
    TIME
    -0.60
    kamp
    -0.60
    MAC
    -0.60
    axter
    -0.59
     Survivors
    -0.59
    POSITIVE LOGITS
     thousand
    1.39
    ousand
    1.09
     dollars
    1.08
     Thousand
    1.01
     metres
    1.00
    ths
    0.98
     miles
    0.97
     eighty
    0.95
     pounds
    0.95
     kilometers
    0.94
    Activations Density 0.027%

    No Known Activations