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

    Neuronpedia

    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. 0-RES-JB
    11. 15586
    Prev
    Next
    INDEX
    Explanations

    phrases related to opposition or conflict

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "against."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    overed
    -0.68
     Highlands
    -0.62
    lder
    -0.57
     Mystery
    -0.56
     cues
    -0.56
     Sunrise
    -0.54
     fanc
    -0.54
    mitter
    -0.53
    aper
    -0.52
    Located
    -0.52
    POSITIVE LOGITS
     against
    3.51
    against
    3.30
     Against
    2.64
    Against
    2.36
     AGA
    1.47
     versus
    1.38
     vs
    1.26
     opposed
    1.21
     defensively
    0.99
     opposing
    0.98
    Activations Density 0.064%

    No Known Activations