© 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. 4-RES-JB
    11. 11000
    Prev
    Next
    INDEX
    Explanations

    mentions of live events or performances

    oai_token-act-pair · gpt-3.5-turbo

    references to live performances or live events

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

    No Comments

    Negative Logits
    akeru
    -0.86
    uyomi
    -0.85
    essee
    -0.84
    unity
    -0.81
    xual
    -0.80
    une
    -0.77
    ificent
    -0.76
    ittee
    -0.76
    adr
    -0.76
    cientious
    -0.75
    POSITIVE LOGITS
    lihood
    1.10
     streaming
    0.86
     broadcasts
    0.84
     Streaming
    0.81
    lier
    0.78
     feed
    0.76
     broadcast
    0.75
     live
    0.74
     feeds
    0.74
     births
    0.73
    Activations Density 0.023%

    No Known Activations