© 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. 1-RES-JB
    11. 20768
    Prev
    Next
    INDEX
    Explanations

    the concept of something being double-edged

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the term "double."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.86
    ä½ľ
    -0.81
    zeb
    -0.76
    doms
    -0.74
    Downloadha
    -0.74
    akeru
    -0.73
    insk
    -0.73
    Introduced
    -0.72
    atche
    -0.72
    argon
    -0.70
    POSITIVE LOGITS
     double
    0.83
    pend
    0.78
    header
    0.77
     sided
    0.73
     dipping
    0.71
     negatives
    0.69
    headers
    0.69
    double
    0.69
     exponential
    0.68
     bluff
    0.68
    Activations Density 0.010%

    No Known Activations