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. 2325
    Prev
    Next
    INDEX
    Explanations

    terms related to software or technology, particularly focusing on specific platforms such as GNOME, KDE, Unity, and Qt

    oai_token-act-pair · gpt-3.5-turbo

    references to specific software and development frameworks related to GNOME and KDE

    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
    ilage
    -0.88
    rieved
    -0.80
    etts
    -0.79
    ihil
    -0.78
    het
    -0.76
    rahim
    -0.76
    hers
    -0.76
    uracy
    -0.76
    oys
    -0.74
    inery
    -0.74
    POSITIVE LOGITS
     KDE
    0.89
     Libre
    0.89
     Plasma
    0.78
     Forums
    0.78
     Keyboard
    0.76
     GNOME
    0.76
     desktop
    0.74
     Graph
    0.72
     Calendar
    0.72
     Orchestra
    0.69
    Activations Density 0.021%

    No Known Activations