© 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. 9-RES-JB
    11. 5250
    Prev
    Next
    INDEX
    Explanations

    electronics and tech-related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of Pokémon descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ïī
    -0.71
    20439
    -0.63
    ο
    -0.62
    Magikarp
    -0.62
     thereof
    -0.61
     thereto
    -0.61
    Õ
    -0.59
    .","
    -0.56
    ¯
    -0.56
    ̶
    -0.56
    POSITIVE LOGITS
    odore
    0.78
    xiety
    0.73
     Overview
    0.72
    achusetts
    0.72
     Releases
    0.72
    resa
    0.70
     Uses
    0.69
     Versus
    0.69
    roximately
    0.69
     vs
    0.68
    Activations Density 0.373%

    No Known Activations