© 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. 21078
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing or describing personal characteristics or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    present tense forms of the verb "to be."

    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
     Inqu
    -0.58
     completes
    -0.54
     LP
    -0.54
     Ll
    -0.53
    iken
    -0.52
     Catalonia
    -0.52
     Guam
    -0.51
     corrid
    -0.51
     Arts
    -0.50
    anos
    -0.50
    POSITIVE LOGITS
     supposed
    0.87
    externalActionCode
    0.80
     relative
    0.76
     gonna
    0.73
    !.
    0.73
     compared
    0.73
    doi
    0.71
    !!!!!!!!
    0.71
    enegger
    0.70
     going
    0.69
    Activations Density 0.077%

    No Known Activations