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

    Neuronpedia

    Jacobian LensNEW
    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. 10881
    Prev
    Next
    INDEX
    Explanations

    references to the tragic events that happened on September 11, 2001 (9/11)

    oai_token-act-pair · gpt-3.5-turbo

    references and content related to the September 11 attacks

    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
     blush
    -0.65
     Dragonbound
    -0.62
    abase
    -0.61
     Syl
    -0.61
    antha
    -0.60
     lettuce
    -0.59
     Opportun
    -0.58
     repro
    -0.57
    ause
    -0.57
     faint
    -0.57
    POSITIVE LOGITS
    11
    0.97
    911
    0.82
    12
    0.82
    13
    0.80
    999
    0.79
    10
    0.77
    9
    0.77
    oct
    0.75
    7
    0.74
    9999
    0.73
    Activations Density 0.038%

    No Known Activations