© 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. 10-RES-JB
    11. 10593
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to opposition or contention

    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 @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oola
    -0.90
    ulous
    -0.89
    çīĪ
    -0.88
    ulously
    -0.85
    chin
    -0.85
    aukee
    -0.76
    hops
    -0.73
    retty
    -0.73
    kered
    -0.73
    ruary
    -0.73
    POSITIVE LOGITS
     whom
    0.93
     Humanity
    0.90
     him
    0.88
     prejudice
    0.82
     tyranny
    0.80
     backdrop
    0.80
     unreasonable
    0.79
     encro
    0.78
     humanity
    0.78
     them
    0.78
    Activations Density 0.071%

    No Known Activations