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. 21215
    Prev
    Next
    INDEX
    Explanations

    phrases related to software functionality

    oai_token-act-pair · gpt-3.5-turbo

    references to software or application capabilities and features

    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
    76561
    -0.83
    ioxide
    -0.74
    earth
    -0.69
     Fever
    -0.68
    wind
    -0.66
    etti
    -0.65
     Citizen
    -0.63
    apers
    -0.63
    vol
    -0.63
     Solo
    -0.62
    POSITIVE LOGITS
    ality
    0.88
    witz
    0.85
     functionality
    0.84
    atility
    0.80
     enhancements
    0.78
    unctions
    0.77
    matically
    0.75
    ivity
    0.73
     Provided
    0.72
    avascript
    0.72
    Activations Density 0.018%

    No Known Activations