© 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. 10-RES-JB
    11. 16128
    Prev
    Next
    INDEX
    Explanations

    nouns related to personal names

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly in a journalistic or documentary context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemTracker
    -0.67
    atism
    -0.67
     narrated
    -0.66
    âĢİ
    -0.59
    ¶
    -0.59
    profits
    -0.58
    \":
    -0.57
    *:
    -0.55
    CVE
    -0.54
    cot
    -0.53
    POSITIVE LOGITS
    utterstock
    0.89
    ulton
    0.83
    reenshot
    0.81
     Shutterstock
    0.74
     IMAGES
    0.73
    Stock
    0.73
    Photo
    0.72
    UTERS
    0.71
    photos
    0.70
    Phot
    0.70
    Activations Density 0.093%

    No Known Activations