© 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. 6148
    Prev
    Next
    INDEX
    Explanations

    proper nouns of people's names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of names, particularly focusing on the name "Roth"

    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
    tics
    -0.69
     Morsi
    -0.66
     PLA
    -0.65
     Demand
    -0.64
     Cortana
    -0.63
     Tube
    -0.62
     Dota
    -0.62
     Advertisement
    -0.61
     Tibet
    -0.61
    ATIONS
    -0.58
    POSITIVE LOGITS
    bard
    1.22
    bart
    1.11
    stein
    1.10
    kj
    0.99
    enei
    0.96
    kefeller
    0.95
    schild
    0.93
    cliffe
    0.93
    child
    0.87
    ough
    0.86
    Activations Density 0.067%

    No Known Activations