© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 20903
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otle
    -0.88
    alle
    -0.81
    bourg
    -0.80
    ocide
    -0.79
    unicip
    -0.78
    ilic
    -0.78
    ciating
    -0.77
    argon
    -0.75
    د
    -0.74
    ioxide
    -0.73
    POSITIVE LOGITS
     IMAGES
    0.67
     LV
    0.64
    plane
    0.64
     Shutterstock
    0.63
     Matter
    0.63
     stret
    0.62
     Above
    0.62
     therapists
    0.61
     providers
    0.61
     ATK
    0.61
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.