© 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. 22344
    Prev
    Next
    INDEX
    Explanations

    specific nutrients and their effects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fatty acids

    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
     ILCS
    -0.68
     Sweeney
    -0.65
    iths
    -0.64
    bourg
    -0.64
    inventoryQuantity
    -0.62
     Berk
    -0.62
    APH
    -0.62
    ONDON
    -0.61
    cast
    -0.60
     GMT
    -0.60
    POSITIVE LOGITS
    yang
    0.76
    rob
    0.71
    shi
    0.67
    rium
    0.66
    urst
    0.64
     Mi
    0.63
    orno
    0.62
    progress
    0.62
    ros
    0.61
    bage
    0.61
    Activations Density 0.000%

    No Known Activations