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. 8667
    Prev
    Next
    INDEX
    Explanations

    numerical expressions referring to a specific quantity

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "single" in various contexts

    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
    akings
    -0.86
    Downloadha
    -0.83
    apons
    -0.76
    raints
    -0.73
     notor
    -0.72
    arium
    -0.72
    ooks
    -0.72
    acists
    -0.69
    enaries
    -0.68
     Hoo
    -0.68
    POSITIVE LOGITS
    handedly
    1.18
     digit
    1.01
    player
    0.92
    ton
    0.91
     digits
    0.87
     minute
    0.86
    digit
    0.83
     sided
    0.82
     parent
    0.81
     molecule
    0.79
    Activations Density 0.017%

    No Known Activations