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. 3-RES-JB
    6. 22285
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingen
    -0.79
    vik
    -0.76
    xon
    -0.72
    catentry
    -0.70
    AE
    -0.70
    beard
    -0.70
    etary
    -0.69
    trop
    -0.69
    aqu
    -0.69
    gallery
    -0.66
    POSITIVE LOGITS
    ullah
    0.66
    Õ
    0.66
     CPC
    0.66
     fam
    0.65
    ``
    0.64
     laun
    0.64
    Tonight
    0.61
    FTWARE
    0.60
    aughter
    0.60
    ï¸ı
    0.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.