© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 19980
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of a person with the name "Condoleezza Rice"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "conditions" or "conditionality."

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

    No Comments

    Negative Logits
    ngth
    -0.77
    ku
    -0.74
    kaya
    -0.74
    DW
    -0.72
    cca
    -0.72
    EStream
    -0.67
    aukee
    -0.65
    Sham
    -0.65
    DIR
    -0.65
    yrim
    -0.63
    POSITIVE LOGITS
    itions
    1.02
    itional
    1.00
    ensed
    0.96
    uctor
    0.91
    ominium
    0.86
    uits
    0.85
    emn
    0.84
    secut
    0.82
    iments
    0.82
    itionally
    0.80
    Activations Density 0.009%

    No Known Activations