© 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. 10-RES-JB
    11. 18775
    Prev
    Next
    INDEX
    Explanations

    strings of numbers and special characters

    oai_token-act-pair · gpt-3.5-turbo

    significant events or milestones in the context of sports or competitive activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     knots
    -0.53
     Slayer
    -0.51
     Gillespie
    -0.51
     Healer
    -0.50
     Malf
    -0.50
     Skinner
    -0.50
    leck
    -0.48
     DPS
    -0.48
     Parenthood
    -0.47
     Pillar
    -0.47
    POSITIVE LOGITS
    published
    0.61
    index
    0.61
    tml
    0.60
    canon
    0.59
    eport
    0.59
    imore
    0.58
    pec
    0.58
    javascript
    0.58
    <|endoftext|>
    0.57
    ribune
    0.56
    Activations Density 0.662%

    No Known Activations