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. 11837
    Prev
    Next
    INDEX
    Explanations

    references to place names, specifically ones containing the character sequence "Ow"

    oai_token-act-pair · gpt-3.5-turbo

    references to the place "Owings County" and associated terms

    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
    bourg
    -0.89
     congr
    -0.80
     centrif
    -0.73
    âĸ¬
    -0.68
    ++++++++++++++++
    -0.65
     fracturing
    -0.65
     Mobil
    -0.62
     MSM
    -0.61
    ugal
    -0.60
    analysis
    -0.60
    POSITIVE LOGITS
     ow
    1.38
    owl
    1.10
     owl
    1.02
    ahoo
    1.00
     Owl
    0.99
    swick
    0.99
    sburg
    0.97
     Ow
    0.94
    ls
    0.85
    yssey
    0.84
    Activations Density 0.022%

    No Known Activations