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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22571
    Prev
    Next
    INDEX
    Explanations

    adjectives describing the quality or nature of something, often with an emphasis on intensity

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers that emphasize the degree or quality of something

    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
    ĸļ
    -1.11
    emale
    -0.82
     TAMADRA
    -0.81
    ICLE
    -0.80
    ACTED
    -0.72
     WATCHED
    -0.70
     Exactly
    -0.67
    isine
    -0.66
     Uriel
    -0.65
    heid
    -0.65
    POSITIVE LOGITS
     shenanigans
    0.86
     goodies
    0.86
    worldly
    0.85
     shenan
    0.85
     tricks
    0.85
     surprises
    0.84
     bumps
    0.79
     quirks
    0.78
    uitous
    0.75
     caveats
    0.74
    Activations Density 0.264%

    No Known Activations