© 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. 18918
    Prev
    Next
    INDEX
    Explanations

    references to objects or activities related to pinball

    oai_token-act-pair · gpt-3.5-turbo

    references to 'pin' and its variations, indicating a focus on items related to 'pin' in various contexts

    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
    anwhile
    -0.90
     behav
    -0.79
    Ö¼
    -0.65
    eger
    -0.64
    ODY
    -0.63
     Equal
    -0.62
     plur
    -0.62
    earch
    -0.62
     Ways
    -0.61
     Continue
    -0.61
    POSITIVE LOGITS
    ning
    1.42
    ned
    1.21
    ball
    1.19
    ochet
    1.16
    ching
    1.15
    keye
    1.13
    ched
    1.06
    wheel
    1.06
    strip
    1.06
    hole
    1.02
    Activations Density 0.028%

    No Known Activations