© 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. 9-RES-JB
    11. 11359
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to equipment or operations

    oai_token-act-pair · gpt-3.5-turbo

    non-standard or unconventional symbols and formatting

    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
     Sob
    -0.88
     Saiyan
    -0.84
     Maker
    -0.83
     Clause
    -0.81
     Conf
    -0.80
     Lib
    -0.80
     Mobil
    -0.80
     Genie
    -0.80
     Camp
    -0.80
     Pr
    -0.79
    POSITIVE LOGITS
    THE
    1.28
    Reviewer
    1.24
    Secondly
    1.23
    Advertisements
    1.23
    another
    1.22
    CONCLUS
    1.21
    advertisement
    1.20
    also
    1.18
    then
    1.18
    WHAT
    1.18
    Activations Density 0.460%

    No Known Activations