© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17646
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "to" or "by" separated by a hyphen

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating measurement or comparison

    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
    orthy
    -0.87
    apolis
    -0.83
    uga
    -0.79
    esta
    -0.79
    iets
    -0.78
    dor
    -0.78
    aceae
    -0.73
    soDeliveryDate
    -0.73
    gart
    -0.73
    ici
    -0.72
    POSITIVE LOGITS
     comparisons
    1.03
     correspondence
    1.02
     transsexual
    0.96
     ratio
    0.91
     conversions
    0.90
     converter
    0.88
     conversion
    0.88
     basis
    0.87
     ratios
    0.84
     comparison
    0.81
    Activations Density 0.140%

    No Known Activations