© 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. 8-RES-JB
    11. 10538
    Prev
    Next
    INDEX
    Explanations

    phrases related to opposition or contradiction

    oai_token-act-pair · gpt-3.5-turbo

    references to concepts of opposition or counter actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roche
    -0.75
     Forge
    -0.67
    OOD
    -0.65
     County
    -0.62
     Erie
    -0.62
     Known
    -0.62
     Tornado
    -0.61
     Unlimited
    -0.60
     Stras
    -0.60
     ABE
    -0.60
    POSITIVE LOGITS
    measures
    1.39
    intuitive
    1.32
    attack
    1.31
    balance
    1.30
    fact
    1.21
    intelligence
    1.20
    balanced
    1.16
    attacks
    1.14
    cultural
    1.12
    mand
    1.11
    Activations Density 0.023%

    No Known Activations