© 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. 6-RES-JB
    11. 9311
    Prev
    Next
    INDEX
    Explanations

    references to specific professions or specialized fields such as police, politics, investments, and medical sciences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to societal issues and health-related topics

    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
    ?).
    -0.64
    )=(
    -0.61
    )."
    -0.59
    %).
    -0.56
    çĶ°
    -0.55
    etheless
    -0.54
    )!
    -0.52
    ļé
    -0.52
    )?
    -0.50
    Else
    -0.50
    POSITIVE LOGITS
    ynthesis
    0.56
    Enlarge
    0.56
     and
    0.54
     or
    0.52
    ,[
    0.52
    ,''
    0.51
    weed
    0.50
    lift
    0.48
    tags
    0.48
    Newsletter
    0.48
    Activations Density 1.038%

    No Known Activations