© 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. 10-RES-JB
    11. 17412
    Prev
    Next
    INDEX
    Explanations

    mentions of statistical data or numerical figures

    oai_token-act-pair · gpt-3.5-turbo

    statistics and numerical data points in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Synopsis
    -0.80
    iquette
    -0.80
     lockdown
    -0.73
    usalem
    -0.72
     exting
    -0.70
    Ñı
    -0.69
     interf
    -0.69
     accomp
    -0.69
     invitation
    -0.69
     grate
    -0.69
    POSITIVE LOGITS
     Median
    1.15
     averages
    1.14
    Average
    1.12
     Adjusted
    1.08
     Compare
    1.07
     median
    1.05
     Numbers
    1.05
     Average
    1.02
     Interestingly
    0.99
    Overall
    0.98
    Activations Density 0.415%

    No Known Activations