© 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. 9-RES-JB
    11. 11467
    Prev
    Next
    INDEX
    Explanations

    locations of press conferences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to press conferences and public statements

    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
    Current
    -0.73
    MAP
    -0.68
    Article
    -0.68
     predators
    -0.67
    Whoever
    -0.67
    usercontent
    -0.66
    Title
    -0.66
    Filter
    -0.65
     infringing
    -0.65
     certs
    -0.64
    POSITIVE LOGITS
    ottage
    0.92
     Seoul
    0.84
     Dull
    0.82
    cheon
    0.79
     Cannes
    0.79
     sidelines
    0.78
     plush
    0.77
     Sao
    0.76
     Cheong
    0.76
     Downing
    0.74
    Activations Density 0.240%

    No Known Activations