© 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. 9-RES-JB
    11. 3302
    Prev
    Next
    INDEX
    Explanations

    dates in the format '9/11'

    oai_token-act-pair · gpt-3.5-turbo

    references to the date September 11th in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blush
    -0.68
     lif
    -0.66
     Opportun
    -0.66
     Bulg
    -0.65
     avail
    -0.63
     MLA
    -0.62
     faint
    -0.62
     bios
    -0.62
     sul
    -0.61
     Leilan
    -0.61
    POSITIVE LOGITS
    11
    1.04
    oct
    0.94
    911
    0.88
    12
    0.87
    13
    0.84
    2012
    0.83
    10
    0.83
    ¶
    0.81
    999
    0.81
    9
    0.81
    Activations Density 0.021%

    No Known Activations