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. 5-RES-JB
    6. 6742
    Prev
    Next
    INDEX
    Explanations

    the last name "Comte"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "te."

    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
    ipolar
    -0.73
     eleph
    -0.68
     pressures
    -0.64
    ĸļ
    -0.63
    interrupted
    -0.62
    lessly
    -0.62
    etheless
    -0.62
    ¥ŀ
    -0.61
     continents
    -0.60
    kernel
    -0.60
    POSITIVE LOGITS
    brate
    1.44
    brates
    1.31
    ller
    1.20
    llers
    1.11
    achers
    1.11
    achable
    1.10
    levision
    1.06
    legraph
    1.05
    legram
    1.04
    aching
    1.02
    Activations Density 0.018%

    No Known Activations