© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 23947
    Prev
    Next
    INDEX
    Explanations

    terms related to the firing, burning, or discharging of something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to combustion or the process of being "fired."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afort
    -0.77
    vas
    -0.74
    los
    -0.73
    doi
    -0.73
    ËĪ
    -0.72
    UFC
    -0.71
     Payne
    -0.70
    aido
    -0.68
    acion
    -0.66
    etics
    -0.64
    POSITIVE LOGITS
    fired
    0.87
     emitting
    0.86
     cleaner
    0.78
     hotter
    0.78
     piping
    0.71
     emits
    0.70
    gency
    0.70
    ricanes
    0.69
    agascar
    0.69
    20439
    0.69
    Activations Density 0.010%

    No Known Activations