© 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. 11-RES-JB
    11. 9464
    Prev
    Next
    INDEX
    Explanations

    instances of individuals meeting or interacting with others

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "meet" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.66
    eware
    -0.64
    vernment
    -0.64
    secution
    -0.63
    oha
    -0.63
    ication
    -0.62
    esm
    -0.61
    creation
    -0.61
    wards
    -0.60
    wcs
    -0.59
    POSITIVE LOGITS
    amorph
    1.39
    ioned
    0.93
    agame
    0.89
     with
    0.89
    ups
    0.88
     privately
    0.86
     up
    0.83
    tle
    0.82
    ropolis
    0.80
     Reincarn
    0.78
    Activations Density 0.050%

    No Known Activations