© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2580
    Prev
    Next
    INDEX
    Explanations

    numerical figures, likely related to financial data or statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly sequences of numbers

    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
    dayName
    -0.81
    igans
    -0.77
    arb
    -0.71
    iencies
    -0.65
    ivari
    -0.65
    rats
    -0.65
    opol
    -0.64
     Lauder
    -0.64
    rooms
    -0.64
    channelAvailability
    -0.63
    POSITIVE LOGITS
    79
    1.00
    74
    0.99
    71
    0.98
    59
    0.97
    04
    0.97
    03
    0.96
    06
    0.94
    07
    0.94
    73
    0.94
    65
    0.92
    Activations Density 0.070%

    No Known Activations