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. 1351
    Prev
    Next
    INDEX
    Explanations

    mentions of a particular town

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Titt" or variations of it

    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
    senal
    -0.72
     womb
    -0.69
    ĸļ
    -0.68
    ¥ŀ
    -0.67
     arteries
    -0.65
    cles
    -0.65
     psychiat
    -0.64
     exha
    -0.62
    BuyableInstoreAndOnline
    -0.62
    Copy
    -0.60
    POSITIVE LOGITS
    sburgh
    1.72
    sburg
    1.03
    leness
    0.95
    elsen
    0.93
    arant
    0.92
    enger
    0.90
    omo
    0.88
    orio
    0.86
    robe
    0.85
    ake
    0.85
    Activations Density 0.017%

    No Known Activations