© 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. 11-RES-JB
    11. 7087
    Prev
    Next
    INDEX
    Explanations

    details related to news articles reporting on various global events and statements made by officials

    oai_token-act-pair · gpt-3.5-turbo
    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
    âĢ¦]
    -1.08
    !]
    -0.97
    âĢ¦âĢ¦
    -0.94
    âĢ¦)
    -0.91
     âĢ¦"
    -0.90
    ––
    -0.87
    âĢ¦âĢ¦âĢ¦âĢ¦
    -0.87
     âĢ¦
    -0.85
    –
    -0.78
    âĢ¦
    -0.78
    POSITIVE LOGITS
     REUTERS
    0.95
    FILE
    0.84
     Reuters
    0.83
     Tayyip
    0.75
    20439
    0.68
    ideshow
    0.67
    Reuters
    0.67
    Shares
    0.65
     OPEC
    0.65
    expected
    0.64
    Activations Density 0.288%

    No Known Activations