© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6795
    Prev
    Next
    INDEX
    Explanations

    references to published content or pub-related terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Pub" and related terms

    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
     autom
    -0.63
     Emmanuel
    -0.63
     Resurrection
    -0.61
     Ellis
    -0.61
     EFF
    -0.60
     suffice
    -0.60
     Tone
    -0.59
     Trayvon
    -0.59
     Archangel
    -0.58
     Gaia
    -0.58
    POSITIVE LOGITS
    lishes
    1.67
    lish
    1.62
    lisher
    1.59
    lique
    1.59
    lishing
    1.57
    escent
    1.47
    lik
    1.25
    lished
    1.11
    bing
    1.06
    li
    1.05
    Activations Density 0.021%

    No Known Activations