© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7942
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "deaf" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "deaf" and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĦ¢
    -0.72
     portfolio
    -0.72
     Exploration
    -0.68
    Trend
    -0.66
     installments
    -0.66
     Investment
    -0.65
     iteration
    -0.64
    ovich
    -0.64
     Growth
    -0.63
     Comb
    -0.62
    POSITIVE LOGITS
     deaf
    4.57
     blind
    1.63
     mute
    1.55
     blindness
    1.29
     Blind
    1.29
     illiter
    1.27
    blind
    1.23
     paralyzed
    1.17
     blinded
    1.16
     auditory
    1.16
    Activations Density 0.015%

    No Known Activations