© 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. 0-RES-JB
    11. 8341
    Prev
    Next
    INDEX
    Explanations

    numbers in the format of '92 followed by one or two digits'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number '92'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hon
    -0.69
     ticking
    -0.68
    ensed
    -0.67
     tangled
    -0.63
     tow
    -0.63
     istg
    -0.63
     destiny
    -0.61
     scr
    -0.61
     five
    -0.59
     fireworks
    -0.59
    POSITIVE LOGITS
    94
    2.92
    91
    2.88
    92
    2.86
    87
    2.82
    93
    2.82
    84
    2.71
    83
    2.67
    82
    2.61
    81
    2.60
    85
    2.59
    Activations Density 0.035%

    No Known Activations