© 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. 4-RES-JB
    11. 10041
    Prev
    Next
    INDEX
    Explanations

    variations of the word 'ind'

    oai_token-act-pair · gpt-3.5-turbo

    words related to indignation or frustration

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

    No Comments

    Negative Logits
    Ĥİ
    -0.80
    sonian
    -0.78
    BuyableInstoreAndOnline
    -0.77
    OPLE
    -0.76
    MQ
    -0.74
    calling
    -0.73
    veyard
    -0.73
     litter
    -0.72
    姫
    -0.72
    zzo
    -0.71
    POSITIVE LOGITS
    ivid
    1.11
    etermin
    1.11
    ented
    1.06
    irect
    0.98
    irection
    0.98
    oled
    0.95
    igo
    0.93
    icative
    0.92
    icol
    0.91
    ependence
    0.90
    Activations Density 0.008%

    No Known Activations