Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 18897
    Prev
    Next
    INDEX
    Explanations

    references to specific publications

    oai_token-act-pair · gpt-3.5-turbo

    references to media publications, particularly Forbes and Rolling Stone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    until
    -0.75
    displayText
    -0.69
    unts
    -0.69
     concession
    -0.66
    ardless
    -0.65
    train
    -0.65
    rar
    -0.62
    abiding
    -0.62
    cue
    -0.61
    artifacts
    -0.60
    POSITIVE LOGITS
     Magazine
    1.72
     magazine
    1.65
    Magazine
    1.41
     magazines
    1.07
     Publishing
    1.01
    azine
    0.95
     columnist
    0.95
     Monthly
    0.94
     Weekly
    0.93
     Illustrated
    0.91
    Activations Density 0.172%

    No Known Activations