© 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. 4123
    Prev
    Next
    INDEX
    Explanations

    medical terms related to the brain

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the brain and cereal products

    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
    CVE
    -0.74
    jury
    -0.71
    edit
    -0.71
     Strauss
    -0.68
     Hunters
    -0.66
     Prospect
    -0.65
     Abel
    -0.63
     Judd
    -0.63
    lihood
    -0.62
     Mayweather
    -0.62
    POSITIVE LOGITS
     Cere
    1.06
     cere
    1.05
    stal
    0.92
    brate
    0.91
    ogly
    0.88
    ocol
    0.86
    utical
    0.82
    mony
    0.80
    otype
    0.80
     Cortex
    0.79
    Activations Density 0.022%

    No Known Activations