© 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. 2824
    Prev
    Next
    INDEX
    Explanations

    questions asking for the location or existence of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases or questions that inquire about locations or missing elements

    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
    advertisement
    -0.78
    ispers
    -0.77
    arios
    -0.77
    oper
    -0.73
    cture
    -0.73
    iors
    -0.72
    ible
    -0.71
    ior
    -0.69
    igmatic
    -0.67
    CHO
    -0.67
    POSITIVE LOGITS
     inspiration
    0.90
     Wald
    0.86
     weakest
    0.81
     money
    0.80
     funds
    0.77
     allegiance
    0.75
     Ãľ
    0.75
     nearest
    0.74
     heaviest
    0.70
     Carmen
    0.70
    Activations Density 0.072%

    No Known Activations