© 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. 11476
    Prev
    Next
    INDEX
    Explanations

    dates and places of birth

    oai_token-act-pair · gpt-3.5-turbo

    biographical information, particularly birth details and family background

    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
     takedown
    -0.85
    ighting
    -0.77
    defense
    -0.76
    uers
    -0.73
     usability
    -0.73
    âĹ¼
    -0.73
    afer
    -0.71
    Reviewed
    -0.70
    casters
    -0.68
    urg
    -0.67
    POSITIVE LOGITS
     eldest
    0.88
     daughter
    0.83
     youngest
    0.82
     surname
    0.80
     son
    0.76
     nephew
    0.76
    daughter
    0.76
     1961
    0.74
     Born
    0.74
     Daughter
    0.73
    Activations Density 0.267%

    No Known Activations