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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 19957
    Prev
    Next
    INDEX
    Explanations

    female names

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly focusing on the names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ounding
    -0.78
    direction
    -0.76
    awar
    -0.74
    istani
    -0.73
    papers
    -0.69
    zag
    -0.69
    haps
    -0.69
    cffff
    -0.69
    tumblr
    -0.68
    roph
    -0.67
    POSITIVE LOGITS
     Gomez
    1.06
     Olson
    1.00
     Kelley
    0.99
     Roe
    0.97
     Roberts
    0.97
     Robinson
    0.96
     Moore
    0.95
     Rivera
    0.92
     Hansen
    0.91
     Carey
    0.91
    Activations Density 0.145%

    No Known Activations