© 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. 2-RES-JB
    11. 15441
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflicts and oppositions

    oai_token-act-pair · gpt-3.5-turbo

    references to actions opposing or resisting various entities or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hops
    -0.84
    OGR
    -0.80
    collar
    -0.78
    pots
    -0.78
    patch
    -0.76
    gow
    -0.74
    earances
    -0.74
    udder
    -0.72
    hack
    -0.72
    overed
    -0.72
    POSITIVE LOGITS
     against
    0.93
     behalf
    0.83
     oppression
    0.78
     Against
    0.76
     whom
    0.75
     prejudice
    0.74
    against
    0.73
     humanity
    0.72
     opponents
    0.72
     Humanity
    0.71
    Activations Density 0.055%

    No Known Activations