© 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. 2233
    Prev
    Next
    INDEX
    Explanations

    mentions of people's professions or roles

    oai_token-act-pair · gpt-3.5-turbo

    the article "a" indicating instances of individuals, roles, or descriptions

    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
    views
    -0.80
    Edit
    -0.75
    querade
    -0.75
    alion
    -0.75
    mares
    -0.74
    iments
    -0.73
    attacks
    -0.73
    fn
    -0.72
    answer
    -0.71
    encies
    -0.69
    POSITIVE LOGITS
     believer
    1.00
     fixture
    0.98
     bit
    0.97
     proud
    0.96
     descendant
    0.95
     tad
    0.93
     member
    0.93
     reluctant
    0.90
     participant
    0.90
     lifelong
    0.88
    Activations Density 0.242%

    No Known Activations