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. 2110
    Prev
    Next
    INDEX
    Explanations

    phrases related to underground structures like burrows

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "bur" related content, particularly burrows

    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
    é¾įå
    -0.85
    )=(
    -0.82
    FTWARE
    -0.77
    å§«
    -0.74
     Nanto
    -0.73
    éĹĺ
    -0.72
    externalActionCode
    -0.71
    Management
    -0.71
     [&
    -0.69
    aunder
    -0.69
    POSITIVE LOGITS
    rito
    1.22
    rowing
    1.14
    rows
    1.12
     bur
    1.10
    pees
    1.09
    rit
    1.06
    pee
    1.05
    row
    1.02
    riter
    0.99
    gey
    0.98
    Activations Density 0.010%

    No Known Activations