© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 19374
    Prev
    Next
    INDEX
    Explanations

    references to technological devices and features

    oai_token-act-pair · gpt-3.5-turbo

    the presence of conjunctions and punctuation in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nem
    -0.68
    tale
    -0.65
     Akin
    -0.60
    itiveness
    -0.60
    piring
    -0.59
     Medina
    -0.58
     Khe
    -0.56
    manship
    -0.56
     Hoff
    -0.56
    ledged
    -0.55
    POSITIVE LOGITS
     thirds
    0.93
    thirds
    0.85
    Unix
    0.80
    pora
    0.68
    headers
    0.68
    pty
    0.66
     forwards
    0.65
     cub
    0.63
    yrinth
    0.62
    termination
    0.61
    Activations Density 0.533%

    No Known Activations