© 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. 2-RES-JB
    11. 4436
    Prev
    Next
    INDEX
    Explanations

    references to agreements or concepts related to non-proliferation policies or treaties

    oai_token-act-pair · gpt-3.5-turbo

    references to non-proliferation and related treaties

    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
    è¦ļéĨĴ
    -0.88
     louder
    -0.71
    æ©
    -0.68
    è¯
    -0.67
     McGee
    -0.66
     Metatron
    -0.65
     Cobra
    -0.63
    çİĭ
    -0.63
     throne
    -0.63
     shuffle
    -0.62
    POSITIVE LOGITS
    profit
    1.02
    profits
    0.95
    fiction
    0.90
    partisan
    0.88
    yss
    0.86
    entimes
    0.82
    ename
    0.81
    sect
    0.76
    requisite
    0.75
    eteen
    0.75
    Activations Density 0.011%

    No Known Activations