© 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. 2-RES-JB
    11. 12033
    Prev
    Next
    INDEX
    Explanations

    words related to conflict, controversy, and opposing viewpoints

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with political tensions and conflicts

    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
    bis
    -0.46
    tein
    -0.42
    yne
    -0.42
    rollers
    -0.41
    origin
    -0.40
     Norn
    -0.40
    fixed
    -0.40
    Purchase
    -0.39
    Fixed
    -0.39
    Mesh
    -0.39
    POSITIVE LOGITS
    terness
    0.52
    itud
    0.51
    lihood
    0.50
    taboola
    0.49
     rhetorical
    0.49
    ĵĺ
    0.46
    emonic
    0.46
    wcs
    0.46
    NetMessage
    0.45
     sadd
    0.45
    Activations Density 2.780%

    No Known Activations