© 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. 0-RES-JB
    11. 22653
    Prev
    Next
    INDEX
    Explanations

    instances of the word "burger."

    oai_token-act-pair · gpt-3.5-turbo

    references to hamburgers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cy
    -0.64
     ceilings
    -0.62
     Poly
    -0.61
     Winds
    -0.60
     lengths
    -0.58
     poles
    -0.58
     Fin
    -0.58
     Cor
    -0.58
     justice
    -0.58
     DX
    -0.58
    POSITIVE LOGITS
    urger
    4.37
    urg
    2.04
     Burger
    1.14
     burger
    1.13
    urst
    1.10
    aughtered
    1.01
     hamb
    0.99
    auer
    0.95
    angler
    0.90
    urga
    0.90
    Activations Density 0.013%

    No Known Activations