© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3309
    Prev
    Next
    INDEX
    Explanations

    mentions of the university "Dalhousie" and related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of the word "Dal," often in relation to academic institutions or notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     slower
    -0.65
     speed
    -0.63
     slack
    -0.61
     prevailing
    -0.60
     speeds
    -0.59
     speedy
    -0.58
     fading
    -0.58
     faster
    -0.58
     disadvantages
    -0.58
     hardened
    -0.57
    POSITIVE LOGITS
    inar
    1.08
    mia
    0.99
    vik
    0.96
    mat
    0.95
    uci
    0.88
    ucc
    0.86
    ry
    0.86
    adier
    0.84
    ston
    0.84
    isco
    0.84
    Activations Density 0.021%

    No Known Activations