© 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. 15980
    Prev
    Next
    INDEX
    Explanations

    words related to weddings or situations where something is being joined together

    oai_token-act-pair · gpt-3.5-turbo

    words related to marriage and commitment

    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
    externalActionCode
    -0.95
    OUP
    -0.79
    vernment
    -0.78
    displayText
    -0.71
    ãģį
    -0.68
    anwhile
    -0.67
    Import
    -0.65
    ostics
    -0.65
    Consumer
    -0.64
    Ô
    -0.63
    POSITIVE LOGITS
    nesday
    1.98
    lock
    1.07
     wed
    1.06
    gie
    0.96
    rox
    0.94
    een
    0.91
    ding
    0.91
    ged
    0.89
    gew
    0.88
    ring
    0.88
    Activations Density 0.013%

    No Known Activations