© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 2094
    Prev
    Next
    INDEX
    Explanations

    technical terms related to various fields like science, research, genetics, and electronics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of high quantities or volumes of information or events

    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
    eka
    -0.72
     Continued
    -0.71
    odan
    -0.65
    vised
    -0.64
    xit
    -0.60
     Higher
    -0.59
    inth
    -0.59
    TPS
    -0.58
    antha
    -0.58
    ħĭ
    -0.57
    POSITIVE LOGITS
     nowadays
    0.89
     crammed
    0.88
     imaginable
    0.78
     stuff
    0.76
     including
    0.74
     besides
    0.73
     converge
    0.71
    rawdownloadcloneembedreportprint
    0.71
     crap
    0.69
     INCLUD
    0.68
    Activations Density 0.587%

    No Known Activations