© 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. 8604
    Prev
    Next
    INDEX
    Explanations

    phrases related to tension or dispute between different entities

    oai_token-act-pair · gpt-3.5-turbo

    topics related to tensions and conflicts between different nations or groups

    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
    ILE
    -0.73
    order
    -0.69
    ords
    -0.69
    aken
    -0.67
    \/\/
    -0.67
    ings
    -0.64
    ions
    -0.64
    aways
    -0.63
    teenth
    -0.63
    toe
    -0.62
    POSITIVE LOGITS
    xual
    0.82
    senal
    0.74
    psey
    0.74
     Concern
    0.73
    videos
    0.73
    MpServer
    0.72
    */(
    0.70
    atisf
    0.69
     tiss
    0.69
    ensical
    0.69
    Activations Density 0.037%

    No Known Activations