© 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. 23247
    Prev
    Next
    INDEX
    Explanations

    explicit mentions of things that are recommended or essential

    oai_token-act-pair · gpt-3.5-turbo

    phrases or words that indicate necessity or obligation

    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
     Pug
    -0.63
     FINAL
    -0.60
     Monument
    -0.59
     Lod
    -0.59
     Vice
    -0.58
     ATL
    -0.57
    irlf
    -0.56
    é¾
    -0.56
    GGGGGGGG
    -0.55
     Dresden
    -0.55
    POSITIVE LOGITS
    ache
    1.14
    ached
    1.13
    angs
    1.12
    aches
    1.12
    afa
    1.06
    ards
    1.04
    ering
    1.04
    ard
    0.95
    ARD
    0.90
    ered
    0.88
    Activations Density 0.044%

    No Known Activations