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. 0-RES-JB
    6. 8613
    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
    berra
    -0.90
    etheless
    -0.83
    ftime
    -0.78
    cellence
    -0.77
    ĪĴ
    -0.72
    \\\\\\\\\\\\\\\\
    -0.70
    obi
    -0.69
     disapp
    -0.69
    EVA
    -0.68
     Palest
    -0.67
    POSITIVE LOGITS
     slightly
    0.84
     somewhat
    0.75
     jokes
    0.71
     downward
    0.70
     lows
    0.66
     strain
    0.66
     significantly
    0.66
     joke
    0.64
     considerably
    0.63
    ãĥĭ
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.