© 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. 7807
    Prev
    Next
    INDEX
    Explanations

    mentions of proper nouns in news or information text

    oai_token-act-pair · gpt-3.5-turbo

    specific names and phrases related to "Lion" and associated terminology

    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
     mathemat
    -0.90
    ulative
    -0.83
    ammy
    -0.79
    missive
    -0.74
     reluct
    -0.74
     Kuh
    -0.70
    nesota
    -0.70
    arcity
    -0.68
    abies
    -0.66
    ESH
    -0.65
    POSITIVE LOGITS
    naire
    0.95
    xon
    0.81
    bell
    0.78
    ning
    0.77
    fire
    0.76
    clair
    0.71
    ball
    0.70
    hao
    0.69
    urnal
    0.68
    beer
    0.67
    Activations Density 0.034%

    No Known Activations