© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 22892
    Prev
    Next
    INDEX
    Explanations

    mentions of famous people, particularly in the realm of entertainment or sports

    oai_token-act-pair · gpt-3.5-turbo

    references to prominent figures and stars in various entertainment fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sth
    -0.68
    ATIONAL
    -0.67
    angan
    -0.66
    DATA
    -0.65
    Operation
    -0.65
    consumer
    -0.62
    administ
    -0.62
    MIT
    -0.61
    awar
    -0.60
    Beer
    -0.59
    POSITIVE LOGITS
    hips
    1.33
    hip
    1.21
    paces
    0.98
     alike
    0.88
     who
    0.87
    acements
    0.85
    mith
    0.84
     vying
    0.79
     collide
    0.78
    ervatives
    0.78
    Activations Density 0.298%

    No Known Activations