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. 9-RES-JB
    6. 21472
    Prev
    Next
    INDEX
    Explanations

    action verbs related to data manipulation and processing

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with data processing and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    humans
    -0.70
    Enough
    -0.58
    endon
    -0.56
     Americas
    -0.54
    ¥µ
    -0.54
     Shack
    -0.53
     Britons
    -0.53
     Sierra
    -0.52
    Tang
    -0.52
     Blacks
    -0.52
    POSITIVE LOGITS
     separately
    1.20
     individually
    1.14
     automatically
    1.12
     periodically
    1.05
     manually
    1.00
     randomly
    1.00
     promptly
    0.99
     anonymously
    0.99
     accordingly
    0.97
     electronically
    0.96
    Activations Density 0.357%

    No Known Activations