© 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. 0-RES-JB
    11. 20497
    Prev
    Next
    INDEX
    Explanations

    terms related to specific names, potentially related to sports teams or players

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names related to people and specific organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Territories
    -0.72
    ometers
    -0.70
    git
    -0.69
    ometer
    -0.69
    icles
    -0.69
    anke
    -0.67
    herent
    -0.67
     Camer
    -0.66
     Tribal
    -0.66
    imeters
    -0.66
    POSITIVE LOGITS
     Hoff
    3.86
     Hof
    1.24
     Fey
    1.22
     Claus
    1.14
     Samp
    1.13
     Pupp
    1.08
     Ajax
    1.04
     Roe
    0.96
     Cater
    0.95
     Wer
    0.94
    Activations Density 0.025%

    No Known Activations