© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 5991
    Prev
    Next
    INDEX
    Explanations

    references to news organization Reuters in sentences

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the news agency Reuters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chest
    -0.78
    inent
    -0.76
    vil
    -0.76
    hma
    -0.73
    pires
    -0.72
    rette
    -0.71
    itar
    -0.71
    itialized
    -0.69
    vol
    -0.69
    Ö¼
    -0.66
    POSITIVE LOGITS
    PLIED
    0.97
     Reuters
    0.83
     REUTERS
    0.82
     Thomson
    0.80
    Reuters
    0.78
    UTERS
    0.77
    AFP
    0.76
     Photographer
    0.73
    externalActionCode
    0.72
     Images
    0.68
    Activations Density 0.006%

    No Known Activations