© 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. 12-RES-JB
    11. 4103
    Prev
    Next
    INDEX
    Explanations

    names of individuals, especially in academic or professional contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to academic credentials and professional titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     tremend
    -1.13
     challeng
    -0.96
     unnecess
    -0.94
     millenn
    -0.89
     feasible
    -0.88
     manageable
    -0.86
     damp
    -0.86
     downright
    -0.85
     manif
    -0.84
     undermin
    -0.83
    POSITIVE LOGITS
     Previously
    1.41
     His
    1.33
     He
    1.30
     Prior
    1.26
     Currently
    1.24
     Recently
    1.21
     Born
    1.20
     Originally
    1.19
     Known
    1.14
     Earlier
    1.11
    Activations Density 0.302%

    No Known Activations