© 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. 11-RES-JB
    11. 18518
    Prev
    Next
    INDEX
    Explanations

    words related to rules, regulations, and instructions

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" and their variations

    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
    theless
    -0.72
    ggles
    -0.71
     Stability
    -0.66
    idable
    -0.62
     Tycoon
    -0.61
     prevail
    -0.61
    urrencies
    -0.60
     coincide
    -0.60
    Õ
    -0.60
    ryu
    -0.60
    POSITIVE LOGITS
     supposed
    1.02
     striving
    1.00
     trying
    0.98
     hoping
    0.98
     aiming
    0.97
     attempting
    0.95
     expecting
    0.94
     referencing
    0.91
     referring
    0.90
     undertaking
    0.90
    Activations Density 0.106%

    No Known Activations