© 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. 4-RES-JB
    11. 15383
    Prev
    Next
    INDEX
    Explanations

    the name "Wade" appearing in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the character Wade from the Deadpool franchise

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

    No Comments

    Negative Logits
    atem
    -0.81
    rador
    -0.80
    inates
    -0.76
    ogy
    -0.76
    undai
    -0.73
    phis
    -0.71
    İĭ
    -0.71
    fman
    -0.71
    ariat
    -0.70
    ractor
    -0.70
    POSITIVE LOGITS
     Wade
    1.03
    nesday
    0.89
     Bauer
    0.86
     Hole
    0.78
     Norton
    0.75
     Phillips
    0.75
     Bosh
    0.74
     Wink
    0.73
     Hampton
    0.71
     Davis
    0.70
    Activations Density 0.005%

    No Known Activations