© 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. 24208
    Prev
    Next
    INDEX
    Explanations

    words related to extreme heat or intensity

    oai_token-act-pair · gpt-3.5-turbo

    letters or symbols frequently occurring together

    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
     Defender
    -0.72
    sama
    -0.69
    grave
    -0.66
     Fantasy
    -0.64
     Yankee
    -0.64
     Wol
    -0.63
     Spo
    -0.62
    EStream
    -0.62
    Hol
    -0.62
    Gil
    -0.62
    POSITIVE LOGITS
    atch
    0.96
    otation
    0.87
    ressed
    0.86
    anging
    0.85
    ared
    0.81
    angs
    0.81
    alyses
    0.80
    ression
    0.80
    ipping
    0.80
    ipped
    0.80
    Activations Density 0.113%

    No Known Activations