© 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. 7467
    Prev
    Next
    INDEX
    Explanations

    phrases related to Martin Luther King Jr

    oai_token-act-pair · gpt-3.5-turbo

    references to Martin Luther and his influence on the civil rights movement

    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
    ILA
    -0.67
    ramid
    -0.67
    Premium
    -0.65
    yx
    -0.64
     Immunity
    -0.64
     Proced
    -0.63
    -----------
    -0.62
    ilk
    -0.61
     Piercing
    -0.61
    GAME
    -0.60
    POSITIVE LOGITS
     Luther
    1.07
    inders
    0.86
    mingham
    0.75
    gement
    0.75
    ijn
    0.73
     Chavez
    0.72
    enburg
    0.71
    itzer
    0.71
    ayson
    0.70
     nailed
    0.70
    Activations Density 0.005%

    No Known Activations