© 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. 4-RES-JB
    11. 17310
    Prev
    Next
    INDEX
    Explanations

    references to an academic discipline or scholarly activity, particularly related to school, academia, or institutions like universities

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "scholar" in various contexts

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

    No Comments

    Negative Logits
    GBT
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.65
     Miranda
    -0.64
    icative
    -0.64
     Grateful
    -0.63
     Pearce
    -0.62
     GEAR
    -0.62
    spring
    -0.61
     measured
    -0.61
     Shelter
    -0.60
    POSITIVE LOGITS
    olars
    1.15
    midt
    1.10
    uler
    1.06
    izophren
    1.05
    arma
    1.03
    olar
    0.95
    thal
    0.95
    ultz
    0.90
    acher
    0.88
    ampions
    0.87
    Activations Density 0.009%

    No Known Activations