© 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. 1-RES-JB
    11. 15848
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific locations and people

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sects or groups related to Shiite Islam

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.92
    é¾įå¥ij士
    -0.79
    oration
    -0.78
    ment
    -0.75
     Pompe
    -0.74
    ãģĨ
    -0.74
    orative
    -0.72
    anwhile
    -0.72
     Triumph
    -0.71
     BART
    -0.70
    POSITIVE LOGITS
     Shi
    1.15
    kees
    0.88
    eworks
    0.85
     Xia
    0.84
    ugi
    0.83
    omi
    0.83
    cipl
    0.81
    agara
    0.79
    atsu
    0.79
    qus
    0.78
    Activations Density 0.003%

    No Known Activations