© 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. 18537
    Prev
    Next
    INDEX
    Explanations

    terms related to data sorting and manipulations

    oai_token-act-pair · gpt-3.5-turbo

    technical descriptions of sorting and organization processes

    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
     Hutch
    -0.64
    cosystem
    -0.62
    ibur
    -0.60
    Technology
    -0.58
    chnology
    -0.57
     whistlebl
    -0.56
    nered
    -0.56
    jah
    -0.56
    ĨĴ
    -0.56
    uine
    -0.54
    POSITIVE LOGITS
     increments
    0.95
     parentheses
    0.90
     duplicate
    0.88
     interpol
    0.86
     subscript
    0.85
     decimal
    0.85
     subtract
    0.84
     Repeat
    0.84
     integers
    0.83
     diagonal
    0.83
    Activations Density 0.755%

    No Known Activations