© 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. 8-RES-JB
    6. 18341
    Prev
    Next
    INDEX
    Explanations

    statistics or numerical information related to various demographic groups

    oai_token-act-pair · gpt-3.5-turbo

    statistical data regarding proportions and percentages related to demographics and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cules
    -0.89
    æĦ
    -0.82
    jad
    -0.71
    ̶
    -0.67
    ĸļ
    -0.67
    xtap
    -0.66
    ĪĴ
    -0.66
    ł
    -0.66
    rings
    -0.66
     flavours
    -0.65
    POSITIVE LOGITS
     uninsured
    0.94
     respondents
    0.86
     households
    0.86
     overall
    0.86
     unemployed
    0.84
     total
    0.80
     attributable
    0.79
     eligible
    0.79
     overweight
    0.78
     births
    0.76
    Activations Density 0.201%

    No Known Activations