© 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. 24098
    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
     WARN
    -0.91
    ãĥ´
    -0.81
    Atl
    -0.77
     destro
    -0.75
    ahime
    -0.74
     confir
    -0.70
    HUD
    -0.70
    DN
    -0.70
    Bloomberg
    -0.70
    COL
    -0.69
    POSITIVE LOGITS
    oise
    0.78
     amenities
    0.71
     Features
    0.66
    avis
    0.62
     Tigers
    0.62
     Karma
    0.62
    emade
    0.60
     Fields
    0.59
     Effects
    0.57
     Procedure
    0.57
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.