Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 5240
    Prev
    Next
    INDEX
    Explanations

    names of people, specifically middle names

    oai_token-act-pair · gpt-3.5-turbo

    distinctive names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciplinary
    -0.69
    agate
    -0.69
    unct
    -0.68
    ecycle
    -0.68
    hex
    -0.64
    cation
    -0.64
    ghai
    -0.62
    icing
    -0.60
    alys
    -0.59
    ococ
    -0.59
    POSITIVE LOGITS
    LEY
    1.48
    SON
    1.47
    WOOD
    1.46
    TON
    1.46
    MAN
    1.41
    HAM
    1.40
    IAN
    1.40
    VILLE
    1.37
    LIN
    1.37
    ERSON
    1.35
    Activations Density 0.203%

    No Known Activations