© 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. 3811
    Prev
    Next
    INDEX
    Explanations

    words related to examinations or investigations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "examination" and its variations

    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
    activated
    -0.73
    gren
    -0.68
    Hero
    -0.65
    sent
    -0.65
    organic
    -0.65
    mic
    -0.65
    absolute
    -0.65
    adding
    -0.61
    joining
    -0.61
    reach
    -0.61
    POSITIVE LOGITS
     examinations
    1.34
     examination
    1.32
     Examination
    1.31
     exams
    1.03
     Exam
    0.99
     exam
    0.99
     examines
    0.91
    ysis
    0.88
     screenings
    0.86
    ptives
    0.84
    Activations Density 0.009%

    No Known Activations