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. 24018
    Prev
    Next
    INDEX
    Explanations

    words related to the ingredient "salt."

    oai_token-act-pair · gpt-3.5-turbo

    words related to sausages or food items containing "sa"

    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
    INGTON
    -0.77
    ãĥ¼ãĥĨãĤ£
    -0.74
    enegger
    -0.71
    DragonMagazine
    -0.71
    hips
    -0.69
    LIN
    -0.66
    hyde
    -0.66
    å§«
    -0.66
     Kits
    -0.64
     Represent
    -0.64
    POSITIVE LOGITS
    pling
    1.28
    ven
    1.15
    plings
    1.11
    arin
    1.05
    ppy
    1.01
    ucer
    1.01
    llan
    1.00
    uth
    1.00
    uten
    0.99
    pp
    0.97
    Activations Density 0.010%

    No Known Activations