© 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. 10-RES-JB
    11. 2889
    Prev
    Next
    INDEX
    Explanations

    references to different levels or categories within a specific system or organization, particularly focusing on the term "Division"

    oai_token-act-pair · gpt-3.5-turbo

    references to sports divisions or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fey
    -0.61
    jamin
    -0.60
    milo
    -0.60
    FORE
    -0.59
    izabeth
    -0.58
    chell
    -0.57
     volunt
    -0.56
    skinned
    -0.56
     Leone
    -0.55
    aimon
    -0.55
    POSITIVE LOGITS
    al
    1.24
    ality
    1.06
    alities
    1.02
    naire
    0.99
    ally
    0.99
    alist
    0.87
    aler
    0.86
    SHIP
    0.85
    wagon
    0.83
    als
    0.83
    Activations Density 0.034%

    No Known Activations