© 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. 20291
    Prev
    Next
    INDEX
    Explanations

    names of famous athletes

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names

    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
     Cherokee
    -0.88
     Anchorage
    -0.86
     Navajo
    -0.85
    olulu
    -0.83
    Methods
    -0.82
    aucus
    -0.80
     Dominion
    -0.79
     Zup
    -0.79
     Tuls
    -0.78
     NTS
    -0.78
    POSITIVE LOGITS
     sacked
    1.13
    otti
    1.04
     midfielder
    1.04
     striker
    1.03
    igne
    1.02
     teammate
    1.00
    ovic
    0.96
     goalkeeper
    0.96
    sson
    0.96
     Racing
    0.96
    Activations Density 0.274%

    No Known Activations