© 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. 0-RES-JB
    11. 1071
    Prev
    Next
    INDEX
    Explanations

    mentions of clothing items like coats

    oai_token-act-pair · gpt-3.5-turbo

    references to coats

    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
    Hub
    -0.68
     Lank
    -0.68
    reporting
    -0.65
     Khe
    -0.65
     Pwr
    -0.65
     Ung
    -0.64
    bidden
    -0.64
     Trend
    -0.63
     referrals
    -0.63
    Trend
    -0.63
    POSITIVE LOGITS
     coat
    4.01
     coats
    3.40
    coat
    3.36
     Coat
    3.00
     coating
    1.90
     jacket
    1.72
     coated
    1.53
     cloak
    1.42
     Jacket
    1.34
     jackets
    1.33
    Activations Density 0.018%

    No Known Activations