© 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. 3318
    Prev
    Next
    INDEX
    Explanations

    adjectives related to strong emotional or artistic impact

    oai_token-act-pair · gpt-3.5-turbo

    terms that describe artistic styles and sensational elements in narratives

    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
    Roy
    -0.73
    cloth
    -0.65
    GAME
    -0.58
    HOU
    -0.58
     Publisher
    -0.58
    minster
    -0.57
    berman
    -0.56
    plom
    -0.56
    massive
    -0.56
     visibly
    -0.55
    POSITIVE LOGITS
    ized
    2.59
    istic
    2.47
    izing
    2.36
    ization
    2.27
    ised
    2.22
    istically
    2.20
    ist
    2.19
    ism
    2.19
    izes
    2.12
    ize
    2.09
    Activations Density 0.218%

    No Known Activations