© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 24005
    Prev
    Next
    INDEX
    Explanations

    phrases related to speaking at a press conference

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "press conference."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     antip
    -0.63
     Haram
    -0.62
    Rom
    -0.61
     romantic
    -0.60
     steril
    -0.59
    osph
    -0.59
    ãģĦ
    -0.59
     upkeep
    -0.59
     locom
    -0.58
     blackmail
    -0.57
    POSITIVE LOGITS
     announcing
    1.31
     convened
    1.05
     unveiling
    0.98
     flanked
    0.88
     held
    0.84
     Minutes
    0.81
     televised
    0.80
     presided
    0.80
     announcement
    0.80
     appearance
    0.79
    Activations Density 0.050%

    No Known Activations