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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 3-RES-JB
    6. 968
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific location - Albany

    oai_token-act-pair · gpt-3.5-turbo

    mentions of locations, specifically the cities of Albany and Harlem

    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
    hered
    -0.84
    rodu
    -0.80
    ening
    -0.80
    quel
    -0.79
    si
    -0.77
    quet
    -0.75
    ãĤº
    -0.74
    fters
    -0.73
    liness
    -0.73
    yll
    -0.72
    POSITIVE LOGITS
    amus
    0.83
     Albany
    0.75
     Shake
    0.74
     Devils
    0.70
    gdala
    0.70
     Peel
    0.70
    shire
    0.65
    é¾įåĸļ士
    0.64
    lehem
    0.63
     Glob
    0.63
    Activations Density 0.016%

    No Known Activations