© 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. 11-RES-JB
    11. 20946
    Prev
    Next
    INDEX
    Explanations

    specific dates and locations in a news article

    oai_token-act-pair · gpt-3.5-turbo

    references to dates and news events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kush
    -0.96
    wine
    -0.96
     Wad
    -0.93
     Sov
    -0.91
     Gaw
    -0.87
    Sov
    -0.83
     wor
    -0.81
    Williams
    -0.80
    ques
    -0.79
    Wilson
    -0.78
    POSITIVE LOGITS
    itri
    0.92
     Pillar
    0.85
     Roberto
    0.83
     24
    0.81
    24
    0.80
    iston
    0.74
     Pri
    0.74
     Instit
    0.73
    iman
    0.73
     244
    0.73
    Activations Density 1.098%

    No Known Activations