© 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. 4-RES-JB
    11. 15298
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MPG
    -0.69
     UNDER
    -0.67
    schild
    -0.67
     ML
    -0.66
     Ceres
    -0.65
    è¦ļéĨĴ
    -0.64
     Birds
    -0.63
     Fortress
    -0.63
     Prison
    -0.63
    doors
    -0.63
    POSITIVE LOGITS
    pmwiki
    1.01
    anmar
    0.82
    nas
    0.81
    imura
    0.79
    irez
    0.77
    ija
    0.69
    idan
    0.69
    license
    0.68
    SPONSORED
    0.67
    iatus
    0.67
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.