© 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. 9-RES-JB
    11. 3514
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to being in a position of authority or responsibility

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups who hold responsibility or authority in various contexts

    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
    enegger
    -0.70
    æĺ
    -0.59
    Ranked
    -0.59
    Boo
    -0.57
    ELL
    -0.57
    eros
    -0.56
    express
    -0.56
    Pass
    -0.56
    imon
    -0.56
     Disabled
    -0.56
    POSITIVE LOGITS
     overseeing
    1.07
     of
    0.97
     thereof
    0.81
    posts
    0.77
    taker
    0.73
    boards
    0.68
    manship
    0.67
    Reviewer
    0.66
    eering
    0.66
     OF
    0.66
    Activations Density 0.028%

    No Known Activations