© 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. 9-RES-JB
    11. 11350
    Prev
    Next
    INDEX
    Explanations

    references to hacking and hacks

    oai_token-act-pair · gpt-3.5-turbo

    references related to hacking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.70
    eele
    -0.65
    obe
    -0.64
    ikk
    -0.64
     Veter
    -0.64
    oplan
    -0.63
     Presbyter
    -0.62
     Leban
    -0.62
    wait
    -0.62
    oran
    -0.61
    POSITIVE LOGITS
    intosh
    1.38
    aday
    0.96
    lar
    0.85
    athon
    0.80
    driver
    0.79
    netic
    0.79
    RF
    0.79
    romising
    0.75
    hent
    0.75
    paces
    0.74
    Activations Density 0.047%

    No Known Activations