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. 8-RES-JB
    6. 8892
    Prev
    Next
    INDEX
    Explanations

    verbs related to possibility, uncertainty, or requirement

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating possibility or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.82
     overseeing
    -0.77
     mindful
    -0.73
     glad
    -0.72
     obsessive
    -0.72
     watching
    -0.72
    Tips
    -0.72
     reckoning
    -0.72
    watching
    -0.71
     cursing
    -0.71
    POSITIVE LOGITS
     contain
    1.28
     originate
    1.23
     belong
    1.23
     undergo
    1.12
     propagate
    1.11
     withstand
    1.10
     exist
    1.10
     correspond
    1.08
     circulate
    1.06
     consist
    1.03
    Activations Density 0.436%

    No Known Activations