© 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. 14909
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names like "Pere" and "Maurice"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals' names

    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
    imation
    -0.82
    ophobia
    -0.74
    ulously
    -0.73
    imates
    -0.68
    opsy
    -0.67
    ulous
    -0.66
    ablishment
    -0.66
     shame
    -0.65
    uments
    -0.65
    aughter
    -0.65
    POSITIVE LOGITS
    mallow
    0.87
    theless
    0.87
     Pere
    0.87
    tti
    0.86
    ãģ¦
    0.85
    gr
    0.78
    gone
    0.77
    ignty
    0.75
    past
    0.74
    ments
    0.74
    Activations Density 0.018%

    No Known Activations