© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2646
    Prev
    Next
    INDEX
    Explanations

    words related to disagreement or opposition

    oai_token-act-pair · gpt-3.5-turbo

    expressions of resistance or opposition to various issues and ideas

    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
    oufl
    -0.66
    argo
    -0.65
    Delivery
    -0.64
     Tycoon
    -0.63
    ching
    -0.63
    ifter
    -0.61
    mberg
    -0.61
    GD
    -0.61
    oiler
    -0.60
    gallery
    -0.59
    POSITIVE LOGITS
     thereto
    1.13
     to
    0.83
     vehemently
    0.82
     stren
    0.78
     against
    0.71
     viewpoints
    0.71
    establishment
    0.71
     stances
    0.71
    ions
    0.68
    naires
    0.68
    Activations Density 0.091%

    No Known Activations