© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 6855
    Prev
    Next
    INDEX
    Explanations

    references to outlaws or cowboys

    oai_token-act-pair · gpt-3.5-turbo

    mentions of outlaws and cowboys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ranged
    -0.95
    esta
    -0.85
    pite
    -0.85
    ibling
    -0.79
    terior
    -0.78
    abases
    -0.78
    veyard
    -0.75
    leased
    -0.74
    eway
    -0.74
    arenthood
    -0.74
    POSITIVE LOGITS
     Cowboy
    0.92
     Commando
    0.86
     Jacket
    0.80
     Tune
    0.78
    maker
    0.77
     cowboy
    0.77
    èĢħ
    0.75
     outlaw
    0.74
     Butcher
    0.69
     Angus
    0.69
    Activations Density 0.026%

    No Known Activations