© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-RES-JB
    11. 9560
    Prev
    Next
    INDEX
    Explanations

    words related to controversial or provocative topics or figures

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities related to governmental or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lauder
    -0.64
    eer
    -0.60
    DEM
    -0.60
    bilt
    -0.58
    enium
    -0.57
     Lear
    -0.57
     Idlib
    -0.57
    mble
    -0.57
    Magikarp
    -0.56
     rout
    -0.56
    POSITIVE LOGITS
    rief
    1.32
    odies
    1.18
    ruary
    1.17
    rities
    1.16
    attery
    1.14
    esides
    1.08
    ishops
    1.07
    amboo
    1.07
    ilingual
    1.06
    ibli
    1.06
    Activations Density 0.050%

    No Known Activations