© 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. 11-RES-JB
    11. 11200
    Prev
    Next
    INDEX
    Explanations

    phrases related to transitions or changes in position or status

    oai_token-act-pair · gpt-3.5-turbo

    instances of official announcements or resignations

    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
    ãĤ¼
    -0.72
    é¾įå¥ij士
    -0.72
    olds
    -0.67
     Contains
    -0.64
     predictive
    -0.63
    WARE
    -0.63
     measuring
    -0.62
    ãĤ´
    -0.62
    76561
    -0.61
    abiding
    -0.60
    POSITIVE LOGITS
     quit
    1.69
     resign
    1.63
     retire
    1.60
     quitting
    1.51
     retirement
    1.49
     resigned
    1.48
     Quit
    1.37
     retiring
    1.36
     resignation
    1.35
     leave
    1.30
    Activations Density 0.452%

    No Known Activations