© 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. 2-RES-JB
    11. 19717
    Prev
    Next
    INDEX
    Explanations

    instances of the word "chalk" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to chalk

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ourke
    -0.78
    ————————
    -0.75
    ECTION
    -0.72
    INA
    -0.71
    ettel
    -0.70
    ————
    -0.66
    çīĪ
    -0.62
    doors
    -0.62
    vae
    -0.62
    ADS
    -0.62
    POSITIVE LOGITS
     chalk
    1.22
    boards
    1.13
    board
    1.01
    Desk
    0.84
    xual
    0.78
    boarding
    0.78
    flake
    0.76
    dule
    0.76
     stripe
    0.73
    books
    0.73
    Activations Density 0.005%

    No Known Activations