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. 1495
    Prev
    Next
    INDEX
    Explanations

    words related to compatibility with different devices or systems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to compatibility and incompatibility

    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
    vern
    -0.82
    esville
    -0.77
    Downloadha
    -0.75
    arcity
    -0.70
    vae
    -0.70
    telling
    -0.67
    gary
    -0.67
    thur
    -0.67
    ibur
    -0.66
    hunt
    -0.65
    POSITIVE LOGITS
     compatibility
    0.88
    atibility
    0.87
     Compatibility
    0.80
     compatible
    0.76
    atible
    0.72
     compat
    0.72
    lihood
    0.71
    icut
    0.71
    Offline
    0.70
    iations
    0.69
    Activations Density 0.019%

    No Known Activations