© 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. 4-RES-JB
    11. 15300
    Prev
    Next
    INDEX
    Explanations

    words related to opposing or voting against something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "against" in various contexts

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

    No Comments

    Negative Logits
    gallery
    -0.86
    pic
    -0.80
    operated
    -0.79
    hack
    -0.79
    hops
    -0.74
    negie
    -0.70
    OGR
    -0.69
    overed
    -0.69
    electric
    -0.68
    gow
    -0.68
    POSITIVE LOGITS
     anybody
    0.81
     blindly
    0.77
     accepting
    0.77
     prejudice
    0.75
     behalf
    0.75
     anyone
    0.73
     austerity
    0.73
     whom
    0.72
     opposing
    0.72
     independence
    0.70
    Activations Density 0.036%

    No Known Activations