© 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. 0-RES-JB
    11. 18832
    Prev
    Next
    INDEX
    Explanations

    references to exams

    oai_token-act-pair · gpt-3.5-turbo

    words related to examinations and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Johnson
    -0.66
     Twe
    -0.65
    ateful
    -0.64
    HEAD
    -0.64
    ogo
    -0.62
     follower
    -0.62
    Johnson
    -0.60
    arel
    -0.59
    landers
    -0.59
     Chain
    -0.59
    POSITIVE LOGITS
     exam
    3.77
     exams
    3.20
     Exam
    2.93
     examinations
    2.64
     examination
    2.45
     Examination
    2.33
     examiner
    2.18
     tests
    1.33
    examination
    1.31
     test
    1.30
    Activations Density 0.019%

    No Known Activations