© 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. 3641
    Prev
    Next
    INDEX
    Explanations

    words related to cooling, such as fans and vents

    oai_token-act-pair · gpt-3.5-turbo

    references to fans and ventilation systems in modern electronics

    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
     Territories
    -0.79
    AAAAAAAA
    -0.74
    buquerque
    -0.73
    ãģĦ
    -0.72
    ãĥ©ãĥ³
    -0.72
     Incarn
    -0.71
    cific
    -0.70
     adolesc
    -0.70
    REAM
    -0.70
     territories
    -0.69
    POSITIVE LOGITS
     heater
    1.14
     oven
    1.03
     capacitor
    1.01
     plun
    0.92
    maid
    0.87
     fitted
    0.85
     projector
    0.85
     hose
    0.85
     nozzle
    0.84
     malfunction
    0.83
    Activations Density 0.123%

    No Known Activations