© 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. 8-RES-JB
    11. 11333
    Prev
    Next
    INDEX
    Explanations

    phrases relating to methods or ways of achieving something

    oai_token-act-pair · gpt-3.5-turbo

    references to methods or ways of achieving something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oos
    -0.71
    aples
    -0.70
    ubb
    -0.66
    @#&
    -0.65
    endas
    -0.63
    omez
    -0.63
     Wink
    -0.62
    ño
    -0.62
     juven
    -0.61
    ONSORED
    -0.61
    POSITIVE LOGITS
    fare
    0.83
     whereby
    0.82
    terday
    0.76
    finding
    0.72
    forward
    0.72
    mith
    0.70
    ivism
    0.70
    chery
    0.69
    ãĥŁ
    0.68
    ivist
    0.66
    Activations Density 0.030%

    No Known Activations