© 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. 14070
    Prev
    Next
    INDEX
    Explanations

    words related to cooking or preparing food

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "steak" and its variations

    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
     Orbit
    -0.71
    etheless
    -0.70
    IFIED
    -0.68
     Phant
    -0.67
     Io
    -0.66
     eleph
    -0.66
    cules
    -0.64
     Transmission
    -0.62
     guiIcon
    -0.62
    nas
    -0.62
    POSITIVE LOGITS
    chnology
    1.07
    pper
    1.00
    ese
    0.96
    chn
    0.95
    ampunk
    0.94
    xton
    0.93
    ppy
    0.92
    ste
    0.91
    pping
    0.89
    achy
    0.88
    Activations Density 0.017%

    No Known Activations