© 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. 12273
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or people

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and grammatical elements within text

    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
     lich
    -1.07
    alore
    -0.94
     Zoro
    -0.92
     lic
    -0.91
     Drupal
    -0.89
     Zup
    -0.87
    orph
    -0.86
     cous
    -0.86
     LEGO
    -0.86
     kidnap
    -0.85
    POSITIVE LOGITS
    Wilson
    2.80
     Wilson
    2.79
     Seahawks
    1.28
     Sherman
    1.28
     Winston
    1.27
     Cox
    1.26
    Russell
    1.21
     Russell
    1.21
     Baldwin
    1.19
     Vick
    1.11
    Activations Density 0.163%

    No Known Activations