© 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. 1-RES-JB
    11. 23231
    Prev
    Next
    INDEX
    Explanations

    mentions of body parts - specifically ears and toes

    oai_token-act-pair · gpt-3.5-turbo

    references to ears

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Proposition
    -0.72
    photos
    -0.71
     Freeman
    -0.71
    athan
    -0.68
    HY
    -0.67
     Mahm
    -0.66
     Leap
    -0.65
    phot
    -0.61
     Griffith
    -0.60
     Pharm
    -0.60
    POSITIVE LOGITS
     ears
    1.68
     ear
    1.26
    piece
    0.99
    pieces
    0.96
     pierced
    0.94
     horns
    0.94
     brim
    0.89
     buds
    0.87
     nodd
    0.85
    rings
    0.84
    Activations Density 0.007%

    No Known Activations