© 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. 4068
    Prev
    Next
    INDEX
    Explanations

    mentions of animal horns

    oai_token-act-pair · gpt-3.5-turbo

    references to rhino horns

    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
     Yoga
    -0.72
     Memor
    -0.70
     Bowling
    -0.69
    reading
    -0.69
    NY
    -0.69
    agall
    -0.66
     Coco
    -0.64
     volunt
    -0.64
     laundry
    -0.62
    Beg
    -0.62
    POSITIVE LOGITS
     horns
    3.89
     horn
    3.49
    horn
    2.65
     Horn
    2.21
     trumpet
    1.43
     sax
    1.23
     Rhino
    1.14
     whistle
    1.14
     roar
    1.02
     hump
    1.01
    Activations Density 0.034%

    No Known Activations