© 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 EvalsExportsinterp-engineNEWAPI 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. 11661
    Prev
    Next
    INDEX
    Explanations

    specific references to the media platform "Huffington Post"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Huffington Post

    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
     blinded
    -0.70
    rers
    -0.67
     geographically
    -0.65
    venants
    -0.64
    rely
    -0.63
     delegated
    -0.63
     substitutes
    -0.63
     functionally
    -0.61
     proced
    -0.61
    quartered
    -0.60
    POSITIVE LOGITS
     Post
    1.05
    Po
    0.90
    Post
    0.87
    ocamp
    0.85
    INGTON
    0.82
    ington
    0.81
    usalem
    0.79
    ignt
    0.79
    ican
    0.78
    izont
    0.78
    Activations Density 0.033%

    No Known Activations