© 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. 11814
    Prev
    Next
    INDEX
    Explanations

    references to the number "Six"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Six"

    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
    amar
    -0.72
    ibr
    -0.67
     cf
    -0.65
    shown
    -0.64
     upd
    -0.61
    ifles
    -0.61
     err
    -0.59
     associate
    -0.57
    íķ
    -0.57
     harmless
    -0.57
    POSITIVE LOGITS
     Six
    3.57
    Six
    2.35
     Seven
    2.14
     Eight
    2.12
     Four
    2.11
     Five
    2.05
     Fif
    1.98
     Twelve
    1.88
     Nine
    1.88
     Eleven
    1.79
    Activations Density 0.013%

    No Known Activations