© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RES-JB
    11. 22429
    Prev
    Next
    INDEX
    Explanations

    the word "press" specifically occurring in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    references to press secretaries and press-related activities

    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
    AppData
    -0.70
     Bailey
    -0.69
    inho
    -0.68
    oshi
    -0.66
     Suns
    -0.65
    abama
    -0.64
    ji
    -0.64
     Vas
    -0.64
     Judah
    -0.64
     Bram
    -0.62
    POSITIVE LOGITS
    urized
    1.53
     conferences
    1.07
     conference
    1.05
    ured
    1.04
    ures
    1.04
     corps
    1.01
     release
    0.97
    conference
    0.97
     secretary
    0.96
    URE
    0.96
    Activations Density 0.032%

    No Known Activations