© 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. 20965
    Prev
    Next
    INDEX
    Explanations

    specific organizations and individuals that have been the subject of news reports

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating news or information being reported

    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
    RFC
    -0.69
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.69
    sed
    -0.68
    warm
    -0.66
    tumblr
    -0.65
    iewicz
    -0.63
    oka
    -0.61
     1914
    -0.59
    Generic
    -0.59
    amiya
    -0.59
    POSITIVE LOGITS
     exclusively
    0.98
     obtained
    0.94
     exclusive
    0.91
     reporting
    0.88
    exclusive
    0.87
     Coverage
    0.87
     reported
    0.86
     scoop
    0.85
     independently
    0.84
     Investigative
    0.84
    Activations Density 0.164%

    No Known Activations