© 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. 6-RES-JB
    11. 23724
    Prev
    Next
    INDEX
    Explanations

    simple and straightforward descriptions or instructions

    oai_token-act-pair · gpt-3.5-turbo

    key phrases related to simplicity and accessibility in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itized
    -0.58
    azeera
    -0.58
    sburg
    -0.58
    Conclusion
    -0.58
    .$
    -0.57
     Lastly
    -0.56
    puff
    -0.54
    pter
    -0.54
    cill
    -0.53
    livion
    -0.53
    POSITIVE LOGITS
    ccording
    0.66
     acronym
    0.64
     hatched
    0.61
     pitted
    0.60
     premise
    0.58
     ostensibly
    0.57
     purported
    0.56
     basically
    0.55
     comprised
    0.55
     lured
    0.55
    Activations Density 1.496%

    No Known Activations