© 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. 11-RES-JB
    11. 5227
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions involving throwing or discarding things

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÃŁ
    -0.76
    TOP
    -0.69
    Eva
    -0.69
    Visual
    -0.68
    CLASSIFIED
    -0.67
    Upload
    -0.66
    ãĢij
    -0.65
    Width
    -0.64
    CLA
    -0.64
    ieth
    -0.63
    POSITIVE LOGITS
     overboard
    1.39
     tant
    1.17
     wrench
    1.01
     grenades
    1.00
     towel
    0.98
     darts
    0.97
     punches
    0.95
     grenade
    0.92
     stones
    0.83
     dart
    0.82
    Activations Density 0.116%

    No Known Activations