© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1778
    Prev
    Next
    INDEX
    Explanations

    academic titles and abbreviations related to medical, psychology, and research fields

    oai_token-act-pair · gpt-3.5-turbo

    titles or credentials of professionals, particularly academic degrees like PhD or MD

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whiff
    -0.75
     fallout
    -0.59
    buster
    -0.58
     EntityItem
    -0.57
     ripple
    -0.56
     blink
    -0.55
    addons
    -0.55
     perks
    -0.54
     bumper
    -0.54
     decency
    -0.53
    POSITIVE LOGITS
    .,
    1.03
    VM
    0.89
    ociate
    0.89
    sych
    0.88
    Assistant
    0.85
     MPH
    0.81
     Candidate
    0.81
    Director
    0.81
    Professor
    0.78
     Associate
    0.76
    Activations Density 0.055%

    No Known Activations