© 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. 12563
    Prev
    Next
    INDEX
    Explanations

    words related to negative consequences or events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of incidents or occurrences

    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
    Recomm
    -0.70
    PLA
    -0.61
    ãĥĥãĥī
    -0.59
    amina
    -0.59
    Materials
    -0.59
     Nicarag
    -0.58
    Brother
    -0.57
    Witness
    -0.57
    iHUD
    -0.57
    orses
    -0.56
    POSITIVE LOGITS
     aren
    1.51
     are
    1.35
     abound
    1.34
     weren
    1.23
     signify
    1.18
     constitute
    1.15
     tend
    1.14
     denote
    1.14
     represent
    1.12
     ARE
    1.10
    Activations Density 0.301%

    No Known Activations