© 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. 10-RES-JB
    11. 6295
    Prev
    Next
    INDEX
    Explanations

    phrases related to public announcements or statements

    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 @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rom
    -0.60
    Creat
    -0.60
    oiler
    -0.60
     beware
    -0.60
     locom
    -0.59
    alys
    -0.58
     Haram
    -0.57
    cephal
    -0.57
    6666
    -0.57
     Authors
    -0.57
    POSITIVE LOGITS
     announcing
    1.36
     convened
    1.14
     unveiling
    1.04
     held
    0.97
     presided
    0.91
     televised
    0.90
     flanked
    0.89
     announcement
    0.87
     attended
    0.86
     Thursday
    0.86
    Activations Density 0.037%

    No Known Activations