© 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. 8-RES-JB
    11. 8187
    Prev
    Next
    INDEX
    Explanations

    URLs starting with "https"

    oai_token-act-pair · gpt-3.5-turbo

    URLs or web links

    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
     destro
    -0.77
     Morse
    -0.73
     Labrador
    -0.70
     polyg
    -0.68
     Meridian
    -0.67
     grav
    -0.65
     neighb
    -0.65
     sided
    -0.63
    rane
    -0.63
     Boh
    -0.63
    POSITIVE LOGITS
    ://
    1.85
    :/
    1.11
    docs
    0.94
    natureconservancy
    0.93
    archive
    0.89
    doi
    0.88
    :\
    0.86
    youtu
    0.84
    books
    0.84
    twitter
    0.83
    Activations Density 0.014%

    No Known Activations