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. 4220
    Prev
    Next
    INDEX
    Explanations

    numerical patterns in text, specifically 2-digit numbers and sequences of numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and age indicators

    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
    ãĤ©
    -0.80
    ashtra
    -0.66
     cleaners
    -0.65
    ucci
    -0.65
    ãĥ£
    -0.64
    isance
    -0.64
    vana
    -0.64
     fung
    -0.63
    iferation
    -0.62
    ãĥ¥
    -0.59
    POSITIVE LOGITS
    deb
    0.66
    DVD
    0.65
    ousand
    0.64
    apore
    0.64
     Samurai
    0.62
    WAY
    0.62
     Sok
    0.60
    eve
    0.60
     poles
    0.60
     Sail
    0.60
    Activations Density 0.221%

    No Known Activations