© 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. 8-RES-JB
    11. 6441
    Prev
    Next
    INDEX
    Explanations

    phrases related to news and promotions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "The" as a reference to publications or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -----------
    -0.71
     repr
    -0.71
    hang
    -0.69
    lication
    -0.68
    mberg
    -0.67
    alone
    -0.67
    ensis
    -0.66
    cki
    -0.66
    shoot
    -0.65
    itures
    -0.64
    POSITIVE LOGITS
     Huffington
    0.89
     Verge
    0.87
    atre
    0.85
     Conversation
    0.83
     Daily
    0.80
     Economist
    0.78
    oret
    0.76
    resa
    0.75
     Netherlands
    0.75
     Chronicle
    0.74
    Activations Density 0.027%

    No Known Activations