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. 1419
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Randall"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Randall."

    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
    enic
    -0.90
    spring
    -0.86
    undai
    -0.81
     Lama
    -0.72
    igree
    -0.72
    ded
    -0.72
    hetically
    -0.72
    yrim
    -0.69
    ombat
    -0.69
    hedral
    -0.68
    POSITIVE LOGITS
     Stephenson
    0.90
    olph
    0.88
     Randolph
    0.83
     Randall
    0.78
     Cobb
    0.76
    stown
    0.74
    adoes
    0.73
     Sawyer
    0.71
     Ul
    0.68
     rand
    0.68
    Activations Density 0.025%

    No Known Activations