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. 7570
    Prev
    Next
    INDEX
    Explanations

    mentions of specific people

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific pronouns and references to individuals, particularly focusing on female pronouns

    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
    igham
    -0.67
    reach
    -0.65
    ¿½
    -0.65
    iHUD
    -0.60
    izo
    -0.58
    ender
    -0.58
     Allied
    -0.58
    isky
    -0.55
    hod
    -0.55
     reperc
    -0.55
    POSITIVE LOGITS
    ï¸ı
    0.80
    xual
    0.71
    Ö¼
    0.69
     respectively
    0.68
    в
    0.66
    anwhile
    0.65
    к
    0.63
    sic
    0.62
    arine
    0.62
    erent
    0.61
    Activations Density 0.623%

    No Known Activations