© 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. 17659
    Prev
    Next
    INDEX
    Explanations

    instances of the word "drop" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific formatting or placeholders in the text

    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
     Aires
    -0.76
    IZE
    -0.73
    eger
    -0.71
    ĺħ
    -0.64
     Gemini
    -0.62
    selves
    -0.62
    auga
    -0.61
     constitu
    -0.61
     Scotia
    -0.61
    ADRA
    -0.61
    POSITIVE LOGITS
    away
    1.40
    outs
    1.30
    ings
    1.25
    aways
    1.21
    athon
    1.17
    back
    1.14
    offs
    1.14
    up
    1.14
    out
    1.12
    able
    1.11
    Activations Density 0.226%

    No Known Activations