© 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. 20502
    Prev
    Next
    INDEX
    Explanations

    various characters that are more than just models for skimpy outfits

    oai_token-act-pair · gpt-3.5-turbo

    sequences of vertical bars

    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
    anium
    -0.81
    alis
    -0.78
    enance
    -0.78
    ancies
    -0.74
    ory
    -0.73
    ixel
    -0.73
    rons
    -0.72
    ypes
    -0.72
    chenko
    -0.71
    ifts
    -0.70
    POSITIVE LOGITS
    cffff
    1.06
    ··
    0.96
     |--
    0.83
     +---
    0.76
     grep
    0.76
    âĢ¢âĢ¢
    0.74
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.74
    cffffcc
    0.73
    ////////////////////////////////
    0.71
    ¯¯¯¯¯¯¯¯
    0.71
    Activations Density 0.022%

    No Known Activations