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. 3-RES-JB
    6. 10016
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Sinclair" or related information

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly the name "Sinclair."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ield
    -0.74
     Qiao
    -0.68
    alo
    -0.67
     Tome
    -0.66
    illard
    -0.66
    erker
    -0.66
    heon
    -0.65
    kill
    -0.64
    ared
    -0.63
    trap
    -0.63
    POSITIVE LOGITS
     Broadcasting
    0.86
    ufact
    0.78
    CTV
    0.78
     Broadcast
    0.76
    iscopal
    0.75
     Sinclair
    0.75
    clair
    0.74
    estine
    0.74
    tsy
    0.73
    theless
    0.73
    Activations Density 0.016%

    No Known Activations