© 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. 0-RES-JB
    11. 16362
    Prev
    Next
    INDEX
    Explanations

    words related to names or titles with special characters in them

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     caller
    -0.77
     Gener
    -0.75
     Mobile
    -0.71
     loyal
    -0.69
     bull
    -0.69
     Agent
    -0.68
     powerful
    -0.67
     flashing
    -0.67
     carrier
    -0.67
     Liberty
    -0.67
    POSITIVE LOGITS
    ø
    4.45
    å
    2.25
    æ
    1.79
    ö
    1.76
    ör
    1.58
     Oslo
    1.54
     Copenhagen
    1.40
     Norwegian
    1.37
    gaard
    1.37
    ä
    1.36
    Activations Density 0.008%

    No Known Activations