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. 6-RES-JB
    6. 18055
    Prev
    Next
    INDEX
    Explanations

    words related to a person named "Gavin"

    oai_token-act-pair · gpt-3.5-turbo

    a specific name, "Gavin," reflecting a focus on identifying individuals associated with events or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    pard
    -0.70
    pel
    -0.70
    fing
    -0.69
    Fram
    -0.69
    asma
    -0.69
    prising
    -0.68
    esome
    -0.67
    restling
    -0.67
    alities
    -0.66
    roots
    -0.65
    POSITIVE LOGITS
     Gavin
    0.85
    avin
    0.81
     Fraser
    0.76
     Davies
    0.72
    iar
    0.72
    ÃŃa
    0.71
    isks
    0.71
     sidx
    0.70
    ussen
    0.70
    ||||
    0.68
    Activations Density 0.056%

    No Known Activations