© 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. 1201
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various institutions or entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of institutions and characters

    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
     Reps
    -0.75
     Perez
    -0.69
     chore
    -0.69
    andra
    -0.67
     SNAP
    -0.66
    nesota
    -0.66
    oops
    -0.66
    EStreamFrame
    -0.65
    Snap
    -0.65
     Pipeline
    -0.65
    POSITIVE LOGITS
     Britann
    4.11
     Albion
    3.08
     Avalon
    1.61
    ynes
    1.18
     mund
    1.08
     Yor
    0.99
     Atlantis
    0.96
     Acad
    0.96
     Bohem
    0.96
     Conan
    0.96
    Activations Density 0.039%

    No Known Activations