© 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. 13120
    Prev
    Next
    INDEX
    Explanations

    press conferences

    oai_token-act-pair · gpt-3.5-turbo

    instances of press or news conferences

    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
    Creat
    -0.63
    oiler
    -0.63
     extrem
    -0.62
    ictionary
    -0.62
    omorph
    -0.60
     beware
    -0.58
    wikipedia
    -0.56
    Chest
    -0.56
    Os
    -0.55
    Rom
    -0.55
    POSITIVE LOGITS
     announcing
    1.44
     convened
    1.10
     unveiling
    1.10
     held
    0.97
     attended
    0.95
     flanked
    0.93
     presided
    0.93
     introducing
    0.93
     televised
    0.90
     marking
    0.89
    Activations Density 0.055%

    No Known Activations