© 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. 6-RES-JB
    11. 5147
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing extreme negativity or finality

    oai_token-act-pair · gpt-3.5-turbo

    the word "utter" and its variations, indicating expressions of emphasis or strong statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actionDate
    -0.82
    OHN
    -0.75
    llah
    -0.73
    amsung
    -0.73
    xual
    -0.71
     Feder
    -0.66
    ACP
    -0.65
    externalActionCode
    -0.64
     Organizations
    -0.63
    Æ
    -0.62
    POSITIVE LOGITS
    ances
    1.19
    ance
    1.09
    most
    0.94
    aneous
    0.84
     amaz
    0.80
    aneously
    0.77
    ness
    0.76
    opard
    0.74
    TY
    0.74
    itarian
    0.74
    Activations Density 0.029%

    No Known Activations