© 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. 1-RES-JB
    11. 16346
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Saharan
    -0.73
    rane
    -0.67
    cha
    -0.65
    lectic
    -0.63
    abus
    -0.62
    eger
    -0.61
     Yong
    -0.61
    onte
    -0.61
    irin
    -0.60
    iang
    -0.60
    POSITIVE LOGITS
    termination
    0.75
    roads
    0.74
     Clause
    0.64
     Archdemon
    0.63
     ponies
    0.62
     Riders
    0.62
     Enlight
    0.61
    cru
    0.61
     prisoners
    0.61
     Crus
    0.60
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.