© 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 EvalsExportsAPI 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. 17685
    Prev
    Next
    INDEX
    Explanations

    rows or instances of things in a sequential order

    oai_token-act-pair · gpt-3.5-turbo

    references to "row" or "rows" in various contexts

    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
    ãĥ¤
    -0.93
    merce
    -0.82
     mathemat
    -0.69
    urated
    -0.69
    ural
    -0.67
    omic
    -0.65
     Rouhani
    -0.64
    enture
    -0.64
    acly
    -0.64
     metic
    -0.64
    POSITIVE LOGITS
    dy
    1.29
    dies
    1.06
    boat
    0.86
    nd
    0.82
    ski
    0.82
    ser
    0.81
     row
    0.81
    Room
    0.81
    rooms
    0.79
    restling
    0.79
    Activations Density 0.014%

    No Known Activations