© 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. 10-RES-JB
    11. 12831
    Prev
    Next
    INDEX
    Explanations

    phrases or words indicating opposition or contrast

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating contrast or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITED
    -0.76
    adows
    -0.76
     Beans
    -0.75
     Annotations
    -0.73
    lov
    -0.72
    Jump
    -0.72
    utters
    -0.72
    acca
    -0.70
     Mush
    -0.70
    beans
    -0.70
    POSITIVE LOGITS
     side
    0.98
     sexes
    0.98
     sides
    0.96
     direction
    0.87
     sex
    0.87
     extremes
    0.86
     hemisphere
    0.86
     gender
    0.82
     poles
    0.80
     ends
    0.77
    Activations Density 0.045%

    No Known Activations