© 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. 1508
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals, particularly focusing on proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to people and institutions, particularly in local governance and education

    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
    ixture
    -0.79
    eus
    -0.75
    zzi
    -0.73
    arette
    -0.70
    arettes
    -0.70
     Scotia
    -0.69
    ubb
    -0.69
    raviolet
    -0.65
    ICES
    -0.65
    gio
    -0.64
    POSITIVE LOGITS
    earch
    0.97
    FORMATION
    0.85
    mith
    0.74
    âĶģ
    0.74
    ModLoader
    0.73
    ocial
    0.73
    chool
    0.72
    nian
    0.71
    hips
    0.71
    CAST
    0.71
    Activations Density 0.082%

    No Known Activations