© 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. 10-RES-JB
    11. 10683
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something is not supported, compatible, allowed, reflected, or directly executable

    oai_token-act-pair · gpt-3.5-turbo

    negations related to compatibility and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    love
    -0.71
    iency
    -0.69
    Topics
    -0.68
     Fol
    -0.68
    Nice
    -0.67
    papers
    -0.66
    Love
    -0.66
    haven
    -0.66
    GRE
    -0.66
    little
    -0.65
    POSITIVE LOGITS
     necessarily
    1.12
     affected
    1.03
     permitted
    1.02
     applicable
    0.94
     included
    0.92
     allowed
    0.92
    icable
    0.91
     affect
    0.90
     guaranteed
    0.87
     counted
    0.87
    Activations Density 0.205%

    No Known Activations