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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19146
    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
     shoulder
    -0.78
     discharged
    -0.77
     spor
    -0.77
     sweats
    -0.75
     carrier
    -0.74
    acea
    -0.74
     heav
    -0.74
     dexter
    -0.73
     redes
    -0.73
     elbow
    -0.72
    POSITIVE LOGITS
    MIT
    0.85
     Especially
    0.82
     Ultimately
    0.78
     Particularly
    0.77
     Ironically
    0.77
    BOOK
    0.76
    Minnesota
    0.75
     Zup
    0.74
     Recall
    0.74
     Also
    0.73
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.