© 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 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. 3-RES-JB
    11. 5629
    Prev
    Next
    INDEX
    Explanations

    words associated with disagreement or disapproval

    oai_token-act-pair · gpt-3.5-turbo

    instances of objections and opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tycoon
    -0.80
    oiler
    -0.74
    rene
    -0.73
    estone
    -0.68
    estones
    -0.67
    ramid
    -0.66
     groove
    -0.66
    negie
    -0.65
    ching
    -0.65
    omic
    -0.63
    POSITIVE LOGITS
    naires
    1.04
     objections
    1.02
     objection
    0.87
    ¿½
    0.86
     vehemently
    0.84
     thereto
    0.82
     stren
    0.78
    quit
    0.75
    naire
    0.74
    aires
    0.74
    Activations Density 0.022%

    No Known Activations