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. 8-RES-JB
    6. 6722
    Prev
    Next
    INDEX
    Explanations

    different categories of people such as those who are unqualified, complete idiots, under-served, low-income, ultra-Orthodox, and hard-liners

    oai_token-act-pair · gpt-3.5-turbo

    terms related to socioeconomic status and qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.73
     Canaver
    -0.68
     sacrament
    -0.63
     Cache
    -0.63
     confir
    -0.61
     acknow
    -0.60
    BuyableInstoreAndOnline
    -0.59
     Curve
    -0.59
     Conquest
    -0.57
     Medina
    -0.56
    POSITIVE LOGITS
    arers
    1.14
    arians
    1.10
    casters
    1.02
    blers
    0.96
    ographers
    0.93
    erers
    0.92
     recipients
    0.92
    hung
    0.92
    payers
    0.90
     enthusiasts
    0.90
    Activations Density 0.741%

    No Known Activations