© 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 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. 9-RES-JB
    11. 15978
    Prev
    Next
    INDEX
    Explanations

    calls to relax and enjoy various activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to enjoyment and relaxation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    so
    -0.69
    £ı
    -0.69
    terday
    -0.65
    Therefore
    -0.63
    Reply
    -0.61
    Same
    -0.61
     mishand
    -0.60
    aneous
    -0.59
    sole
    -0.59
     wrongly
    -0.58
    POSITIVE LOGITS
     yourselves
    1.51
     yourself
    1.40
     Yourself
    1.06
     your
    1.01
     ;)
    0.99
     yours
    0.97
    !
    0.89
    )!
    0.86
     YOUR
    0.85
     ðŁĻĤ
    0.84
    Activations Density 0.539%

    No Known Activations