© 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. 8-RES-JB
    11. 3063
    Prev
    Next
    INDEX
    Explanations

    keywords related to scientific research and studying various phenomena

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the study and understanding of scientific topics

    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
    appointed
    -0.76
    guard
    -0.72
    WARNING
    -0.70
    advertising
    -0.70
    ©¶æ¥µ
    -0.69
     slapped
    -0.69
    Finish
    -0.69
    Guard
    -0.68
    cil
    -0.66
    utor
    -0.66
    POSITIVE LOGITS
     trends
    0.99
     heterogeneity
    0.97
     genomes
    0.96
     correlations
    0.95
     populations
    0.94
     patterns
    0.93
     biomark
    0.92
     phenomena
    0.91
     how
    0.89
     dynamics
    0.89
    Activations Density 0.253%

    No Known Activations