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. 19037
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations, specifically focusing on places like Mainland, races, upper levels, courts, and tiers

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to social class and legal terminology

    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
    CVE
    -0.66
    CDC
    -0.59
     hotline
    -0.59
    sand
    -0.59
     Cock
    -0.58
     Cly
    -0.58
    dL
    -0.57
     Garage
    -0.57
     Jungle
    -0.56
     Blazing
    -0.55
    POSITIVE LOGITS
    than
    1.68
     than
    1.44
     Than
    1.05
    arsity
    0.80
    anguage
    0.77
     wiser
    0.77
    uries
    0.74
     installments
    0.70
    models
    0.69
    ategories
    0.67
    Activations Density 0.255%

    No Known Activations