© 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. 7-RES-JB
    11. 24017
    Prev
    Next
    INDEX
    Explanations

    information or statements in a text that someone has pointed out or emphasized

    oai_token-act-pair · gpt-3.5-turbo

    references to people making observations or comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.82
    DAQ
    -0.76
     Seym
    -0.73
    inventoryQuantity
    -0.70
    thood
    -0.65
    hene
    -0.64
     ILCS
    -0.63
    ingham
    -0.62
    OOL
    -0.61
    urity
    -0.61
    POSITIVE LOGITS
     pointed
    0.96
     pointing
    0.93
     blank
    0.80
    lessly
    0.77
     toward
    0.76
     finger
    0.74
    points
    0.74
     fingers
    0.73
    point
    0.70
     Reyes
    0.69
    Activations Density 0.032%

    No Known Activations