© 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. 8-RES-JB
    11. 3444
    Prev
    Next
    INDEX
    Explanations

    relationships between individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to friends and acquaintances in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ooks
    -0.80
    ories
    -0.77
     instruments
    -0.73
    Frames
    -0.72
    poons
    -0.71
    bows
    -0.71
    eeds
    -0.70
    ernels
    -0.70
     calendars
    -0.69
    ovies
    -0.69
    POSITIVE LOGITS
     who
    1.25
     whom
    1.16
     whose
    1.10
     named
    1.10
    who
    1.00
    whose
    0.91
    friend
    0.90
     nicknamed
    0.84
     classmate
    0.83
    lier
    0.81
    Activations Density 0.262%

    No Known Activations