© 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. 6-RES-JB
    11. 12317
    Prev
    Next
    INDEX
    Explanations

    phrases that contrast two different options

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating contrast or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.73
    inho
    -0.71
    ells
    -0.67
    boys
    -0.66
     Chips
    -0.64
     Loaded
    -0.63
    avan
    -0.63
    liam
    -0.63
    obyl
    -0.61
     Bras
    -0.61
    POSITIVE LOGITS
    itably
    0.87
     necessarily
    0.75
    isons
    0.69
     opposed
    0.69
    âĶĢâĶĢâĶĢâĶĢ
    0.69
    untarily
    0.68
     materially
    0.68
    entimes
    0.68
    viously
    0.67
     willingly
    0.67
    Activations Density 0.010%

    No Known Activations