© 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. 6-RES-JB
    11. 16865
    Prev
    Next
    INDEX
    Explanations

    instances where an event or interaction happens directly between individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "in person."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    outer
    -0.72
     Tories
    -0.65
     Conservatives
    -0.63
    enthal
    -0.62
    rix
    -0.62
     Balanced
    -0.62
    sweet
    -0.61
    YP
    -0.61
     Penalty
    -0.60
    Tex
    -0.60
    POSITIVE LOGITS
    atown
    0.90
    othe
    0.81
    ividual
    0.78
    ascus
    0.76
    ograph
    0.76
    igraph
    0.74
    afort
    0.73
    atur
    0.72
    atural
    0.71
    ographed
    0.70
    Activations Density 0.017%

    No Known Activations