© 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. 14094
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the assessment of a situation or behavior

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating strong assertions or statements

    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
     Turns
    -0.74
    ãĥĪ
    -0.74
    ©¶æ¥µ
    -0.74
    ËĪ
    -0.69
    luaj
    -0.69
    ãĤ®
    -0.66
     sidx
    -0.65
     Lau
    -0.64
     accuses
    -0.63
     hawk
    -0.62
    POSITIVE LOGITS
     imperative
    1.06
     unacceptable
    1.05
     testament
    0.97
     hereby
    0.96
     uncons
    0.95
     something
    0.95
     vit
    0.95
     paramount
    0.94
     regrett
    0.94
     urgent
    0.93
    Activations Density 0.192%

    No Known Activations