© 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. 17568
    Prev
    Next
    INDEX
    Explanations

    text related to sports events or competitions

    oai_token-act-pair · gpt-3.5-turbo

    structured data formats or references in a technical context

    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
    •EggList

    No Comments

    Negative Logits
     Slayer
    -0.86
     276
    -0.71
     275
    -0.70
     Slaughter
    -0.69
     271
    -0.69
     BU
    -0.68
     274
    -0.67
     Pigs
    -0.67
     273
    -0.67
     Manson
    -0.67
    POSITIVE LOGITS
    e
    1.56
    ey
    1.37
    ec
    1.32
    ef
    1.31
    ean
    1.28
    eu
    1.27
    eh
    1.25
    eb
    1.22
    E
    1.22
    eg
    1.21
    Activations Density 0.257%

    No Known Activations