© 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. 294
    Prev
    Next
    INDEX
    Explanations

    terms related to nature and physical structures

    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
    mitt
    -0.63
    annot
    -0.58
     }}
    -0.58
    alach
    -0.56
    oubted
    -0.56
    nces
    -0.54
    minent
    -0.53
    )</
    -0.53
    ificantly
    -0.53
    exist
    -0.51
    POSITIVE LOGITS
     so
    1.28
     lest
    1.08
    so
    1.06
     thereby
    0.94
     allowing
    0.89
     ensuring
    0.86
     to
    0.84
     hoping
    0.80
     enabling
    0.78
     creating
    0.78
    Activations Density 1.189%

    No Known Activations