© 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. 13137
    Prev
    Next
    INDEX
    Explanations

    references to notable figures or individuals mentioned in a formal context, such as statements made by Justice Marshall or Farmer

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and their statements or actions

    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
     actionGroup
    -0.88
    adelphia
    -0.62
    ļéĨĴ
    -0.60
    clone
    -0.60
    aste
    -0.59
    éĩ
    -0.57
    cellence
    -0.57
     âĸº
    -0.55
     (>
    -0.55
    nob
    -0.55
    POSITIVE LOGITS
     reasoned
    1.33
     argued
    1.13
     argues
    1.13
     contends
    1.06
     contended
    1.03
     says
    1.00
     contend
    0.99
     said
    0.97
     argue
    0.96
     asserted
    0.96
    Activations Density 0.211%

    No Known Activations