© 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. 8-RES-JB
    11. 6808
    Prev
    Next
    INDEX
    Explanations

    mentions of burgers

    oai_token-act-pair · gpt-3.5-turbo

    references to burgers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inel
    -0.79
    agall
    -0.77
    agnetic
    -0.72
    uchin
    -0.70
    nces
    -0.70
    scrib
    -0.69
    perse
    -0.67
     Emin
    -0.67
    oral
    -0.66
    asio
    -0.65
    POSITIVE LOGITS
     burger
    0.93
     burgers
    0.90
    urger
    0.89
     steak
    0.85
    balls
    0.83
     hamb
    0.81
    ards
    0.81
    becue
    0.81
     joints
    0.81
    cake
    0.78
    Activations Density 0.038%

    No Known Activations