© 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. 20436
    Prev
    Next
    INDEX
    Explanations

    technical or clearly defined terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express certainty or qualifications concerning definitions and conditions

    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
    regate
    -0.89
    ults
    -0.78
    atem
    -0.75
    iak
    -0.73
    ERAL
    -0.72
    merga
    -0.72
    eral
    -0.72
    amins
    -0.72
     Flavoring
    -0.70
    States
    -0.70
    POSITIVE LOGITS
     incompatible
    0.87
     irrelevant
    0.85
     preferable
    0.85
     going
    0.84
     safer
    0.80
     indicative
    0.79
     easier
    0.77
     unsustainable
    0.76
     impressive
    0.76
     redundant
    0.76
    Activations Density 0.209%

    No Known Activations