© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 10662
    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
    oqu
    -0.38
    hern
    -0.37
    artisan
    -0.37
    optional
    -0.36
     Railroad
    -0.36
    sole
    -0.35
    claimed
    -0.34
    erness
    -0.34
    adj
    -0.34
     Airl
    -0.32
    POSITIVE LOGITS
     punches
    0.41
    ãĥ£
    0.39
    isons
    0.37
    ãĤ©
    0.36
    oes
    0.35
    ãĥ¼ãĥĨãĤ£
    0.35
    furt
    0.32
    ãĥ¥
    0.32
    Cs
    0.32
     cohorts
    0.32
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.