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. 16855
    Prev
    Next
    INDEX
    Explanations

    the name "Butts"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix "ts"

    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
    vernment
    -0.76
    Reviewer
    -0.73
     livest
    -0.69
     [|
    -0.66
     slic
    -0.66
     suspic
    -0.65
     segments
    -0.64
     ANC
    -0.63
    inventoryQuantity
    -0.62
     JPM
    -0.62
    POSITIVE LOGITS
    weet
    1.22
    hirt
    1.15
    leeve
    1.11
    heet
    1.04
    ween
    1.02
    ember
    1.00
    rue
    1.00
    hower
    1.00
    onic
    0.97
    arah
    0.96
    Activations Density 0.019%

    No Known Activations