© 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. 11-RES-JB
    11. 454
    Prev
    Next
    INDEX
    Explanations

    verbs related to destructive actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to destruction or significant transformation

    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
    LOS
    -0.64
    CHR
    -0.64
    enegger
    -0.63
    lash
    -0.63
     princ
    -0.63
    MY
    -0.60
     writ
    -0.59
    fulness
    -0.59
    PO
    -0.58
    rock
    -0.58
    POSITIVE LOGITS
    ated
    2.54
    ating
    2.46
    ates
    2.32
    ate
    2.29
    ATED
    1.93
    ation
    1.89
    ators
    1.87
    ator
    1.86
    ATING
    1.79
    ations
    1.74
    Activations Density 0.088%

    No Known Activations