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. 0-RES-JB
    6. 21109
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ń·
    -0.71
     Butterfly
    -0.71
    gers
    -0.70
     themselves
    -0.65
     yourselves
    -0.64
     herself
    -0.63
     yourself
    -0.63
    water
    -0.62
     rinse
    -0.62
     trail
    -0.61
    POSITIVE LOGITS
    nil
    0.86
    lesiastical
    0.72
    lesi
    0.71
    inished
    0.71
    ©¶æ
    0.70
     coerc
    0.68
    rahim
    0.68
    onne
    0.67
    ulous
    0.67
    tml
    0.67
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.