© 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. 4478
    Prev
    Next
    INDEX
    Explanations

    specific numerical locations within a document, such as room numbers

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

    references to specific rooms or spaces

    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
     Iss
    -0.69
    Vill
    -0.64
     Yards
    -0.63
     fisherman
    -0.61
     hurd
    -0.59
     Trails
    -0.58
    actionDate
    -0.58
     Rivals
    -0.58
     veh
    -0.57
    HER
    -0.57
    POSITIVE LOGITS
    lain
    1.09
    ful
    1.01
     upstairs
    1.00
     divid
    0.99
     occupancy
    0.98
    itory
    0.91
     adjoining
    0.90
    warming
    0.88
     downstairs
    0.85
     furnished
    0.84
    Activations Density 0.086%

    No Known Activations