© 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. 2-RES-JB
    11. 23984
    Prev
    Next
    INDEX
    Explanations

    references to fur or fur-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to fur, particularly its use in garments and trade

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ysis
    -0.70
     Meier
    -0.69
    ECH
    -0.67
     Mald
    -0.66
    tical
    -0.65
     Defenders
    -0.65
     Nurs
    -0.63
     Bayer
    -0.63
     Barth
    -0.62
     Goddard
    -0.62
    POSITIVE LOGITS
    fur
    1.24
    thur
    1.18
    rier
    1.00
     fur
    1.00
    rows
    0.93
    isode
    0.90
    geons
    0.86
    hair
    0.84
    balls
    0.83
     Fur
    0.83
    Activations Density 0.013%

    No Known Activations