© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 5223
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    »Ĵ
    -1.18
    ãĥ¼ãĥĨãĤ£
    -0.98
    ĪĴ
    -0.93
    Īè
    -0.91
     neighb
    -0.91
    £ı
    -0.91
    Ĭ±
    -0.87
    é¾įå
    -0.86
     disapp
    -0.85
    Ĥ¬
    -0.85
    POSITIVE LOGITS
     Temper
    0.71
     La
    0.71
     imper
    0.68
     Imper
    0.68
     Flores
    0.67
    cci
    0.67
     Por
    0.64
    cu
    0.64
     VP
    0.64
     Mar
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.