© 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. 1-RES-JB
    11. 5099
    Prev
    Next
    INDEX
    Explanations

    phrases related to strong emphasis or precision

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "nail" and its various contextual uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reserved
    -0.87
    ioch
    -0.77
    reen
    -0.70
    sem
    -0.70
    ais
    -0.68
    REDACTED
    -0.68
    =-=-=-=-=-=-=-=-
    -0.67
    eded
    -0.66
    ult
    -0.65
    iety
    -0.65
    POSITIVE LOGITS
     nail
    1.54
     nails
    1.42
     polish
    1.05
     salon
    0.92
    anguage
    0.87
    odon
    0.84
     nailed
    0.82
     hammered
    0.80
     biting
    0.74
     fungus
    0.73
    Activations Density 0.008%

    No Known Activations