© 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. 3731
    Prev
    Next
    INDEX
    Explanations

    words related to academic or technical contexts, specifically focusing on studying or analyzing specific subjects

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "study" and related academic terms

    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
    ulton
    -0.76
     Afghanistan
    -0.70
     Algeria
    -0.69
    opsy
    -0.67
     Yemen
    -0.67
     indigenous
    -0.67
     Mali
    -0.66
     conscious
    -0.66
     Somalia
    -0.64
     Alger
    -0.63
    POSITIVE LOGITS
    ded
    1.16
     stud
    1.15
    ious
    0.98
    ding
    0.98
    Stud
    0.96
    kered
    0.95
    sonian
    0.87
     Stud
    0.86
    ible
    0.85
    iously
    0.84
    Activations Density 0.007%

    No Known Activations