© 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. 10-RES-JB
    11. 12833
    Prev
    Next
    INDEX
    Explanations

    specific media outlet references, particularly "Times"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Times," particularly in the context of news or media articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rd
    -0.87
    leased
    -0.76
    rous
    -0.75
    tesy
    -0.72
    vae
    -0.70
    dyl
    -0.69
    keyes
    -0.68
    isable
    -0.68
    uties
    -0.68
    lain
    -0.67
    POSITIVE LOGITS
     Literary
    1.21
     bestselling
    1.11
     Magazine
    1.01
     Square
    0.92
     Newsp
    0.91
     Dispatch
    0.90
     Herald
    0.87
    '
    0.86
     Higher
    0.85
     columnist
    0.83
    Activations Density 0.026%

    No Known Activations