© 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. 10-RES-JB
    11. 20262
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual, "Wayne."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rador
    -1.00
    gently
    -0.90
    */(
    -0.88
    TAIN
    -0.79
    thumbnails
    -0.79
    yrinth
    -0.78
    dayName
    -0.75
    stood
    -0.74
    hips
    -0.73
    imony
    -0.72
    POSITIVE LOGITS
     Gret
    1.15
     Rooney
    1.13
     Manor
    0.80
     Coy
    0.79
     Enterprises
    0.79
     Dup
    0.76
     Barrett
    0.76
     Wayne
    0.72
     Lug
    0.72
     Swan
    0.71
    Activations Density 0.021%

    No Known Activations