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. 20273
    Prev
    Next
    INDEX
    Explanations

    requirements or prerequisites for various actions or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to requirements or prerequisites

    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
    =]
    -0.78
    alde
    -0.76
    anian
    -0.69
    rift
    -0.69
    owler
    -0.69
    oday
    -0.67
    Sax
    -0.67
     floated
    -0.67
    umbered
    -0.65
    jri
    -0.65
    POSITIVE LOGITS
     upkeep
    0.79
     overtime
    0.78
     approval
    0.71
     permission
    0.69
     signature
    0.69
     fines
    0.68
     deductions
    0.68
     Saturdays
    0.67
     dexterity
    0.67
     fees
    0.66
    Activations Density 0.180%

    No Known Activations