© 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. 11-RES-JB
    11. 14667
    Prev
    Next
    INDEX
    Explanations

    numbers representing specific weeks in a sports-related context

    oai_token-act-pair · gpt-3.5-turbo

    references to specific weeks in a sports context

    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
     distress
    -0.76
     denomin
    -0.72
     emot
    -0.67
     conscientious
    -0.67
     rhy
    -0.67
     stamp
    -0.67
     reflected
    -0.66
     seismic
    -0.66
     glaring
    -0.66
     pulse
    -0.66
    POSITIVE LOGITS
     Two
    1.10
     Seven
    1.10
     Four
    1.07
     Five
    1.06
     Six
    1.06
     Three
    1.06
     1
    1.05
     7
    1.04
     Eleven
    1.04
     Eight
    1.02
    Activations Density 0.045%

    No Known Activations