© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18794
    Prev
    Next
    INDEX
    Explanations

    references to the date "9/11."

    oai_token-act-pair · gpt-3.5-turbo

    references to the date "9/11" and its associated events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mine
    -0.67
     Judd
    -0.63
     pause
    -0.62
     recogn
    -0.61
    stood
    -0.61
     Adv
    -0.61
     Jagu
    -0.60
    ivari
    -0.59
     Compass
    -0.59
     faint
    -0.58
    POSITIVE LOGITS
    9999
    1.16
    999
    1.12
    NEWS
    1.03
    090
    1.00
    001
    0.98
    05
    0.89
    07
    0.88
    06
    0.88
    02
    0.88
    04
    0.86
    Activations Density 0.041%

    No Known Activations