© 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. 7936
    Prev
    Next
    INDEX
    Explanations

    adjectives describing physical characteristics

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to physical attributes and conditions

    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
     inst
    -0.80
     thrill
    -0.67
     tract
    -0.65
     salary
    -0.63
     jur
    -0.63
     Tik
    -0.61
     DW
    -0.61
     Uri
    -0.61
     stake
    -0.61
     sell
    -0.60
    POSITIVE LOGITS
    haired
    2.02
    owsky
    1.89
    ockey
    1.80
    broken
    1.73
    perfect
    1.67
    horn
    1.32
    ovsky
    1.19
    bull
    1.15
    poll
    1.14
    skinned
    1.10
    Activations Density 0.037%

    No Known Activations