Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 17875
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ãĥ
    -0.69
    izations
    -0.64
    èª
    -0.64
    éĽ
    -0.63
     hypot
    -0.62
    tumblr
    -0.62
    etsk
    -0.61
    acity
    -0.60
    apper
    -0.60
    width
    -0.59
    POSITIVE LOGITS
    rozen
    0.65
    enged
    0.61
    bage
    0.61
     grou
    0.59
     rounding
    0.59
    awed
    0.58
    bytes
    0.57
     rele
    0.57
     Shape
    0.57
     sealed
    0.57
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.