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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 125
    Prev
    Next
    INDEX
    Explanations

    instances where people come together

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "gather" and its variations, indicating a focus on the concept of gathering or assembly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    gather

    np_max-act-logits · gemini-2.0-flashTriggered by @johnny
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    void
    -0.78
    incarn
    -0.77
    ck
    -0.76
    infect
    -0.72
    thro
    -0.71
    etheless
    -0.71
    ysis
    -0.69
    geon
    -0.69
    hal
    -0.69
    opathy
    -0.67
    POSITIVE LOGITS
     signatures
    0.93
    ãĤ¤ãĥĪ
    0.86
    ivities
    0.84
     attendees
    0.82
     gathering
    0.81
     gathered
    0.76
     Gathering
    0.76
    itud
    0.73
    STON
    0.73
    DragonMagazine
    0.73
    Activations Density 0.034%

    No Known Activations