© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5604
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing food or nourishment

    oai_token-act-pair · gpt-3.5-turbo

    references to sustenance or nourishment

    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
    isms
    -0.65
    isman
    -0.64
    ijn
    -0.62
    istically
    -0.62
    aries
    -0.60
    vu
    -0.59
    ancouver
    -0.59
     Beach
    -0.57
    butt
    -0.57
    asar
    -0.57
    POSITIVE LOGITS
    stocks
    1.03
    parser
    0.92
    oras
    0.84
    stock
    0.84
    fed
    0.84
    forward
    0.83
    waukee
    0.83
     fed
    0.82
    pread
    0.76
     feeds
    0.76
    Activations Density 0.019%

    No Known Activations