© 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. 1-RES-JB
    11. 24272
    Prev
    Next
    INDEX
    Explanations

    references to specific news publications, particularly the "Washington Examiner"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "examiner" in various contexts, particularly related to medical and investigative roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hold
    -0.79
    eworld
    -0.79
    rams
    -0.73
    rol
    -0.72
    king
    -0.70
     Gandhi
    -0.70
    Saharan
    -0.69
    apo
    -0.69
    plant
    -0.69
    forced
    -0.69
    POSITIVE LOGITS
     Examiner
    1.37
    aminer
    0.85
     examiner
    0.83
     resil
    0.81
    olicy
    0.73
    ILY
    0.72
     reviewers
    0.71
     reviewer
    0.67
    ertodd
    0.66
    imedia
    0.66
    Activations Density 0.012%

    No Known Activations