© 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. 1-RES-JB
    11. 20873
    Prev
    Next
    INDEX
    Explanations

    references to specific times or schedules, particularly mentioning "ET" (Eastern Time)

    oai_token-act-pair · gpt-3.5-turbo

    references to the Entertainment Tonight (ET) television show

    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
    ãĥ´ãĤ¡
    -0.88
    Scotland
    -0.86
    SourceFile
    -0.79
    Ô
    -0.78
    é¾įå
    -0.75
    ł
    -0.75
    ãĥ¼ãĥ³
    -0.72
    ãĥĩ
    -0.71
    stant
    -0.71
    character
    -0.71
    POSITIVE LOGITS
     ET
    1.22
     contrace
    0.77
    ecided
    0.75
    iquette
    0.73
    ICAN
    0.73
    DERR
    0.72
     targ
    0.70
     hatch
    0.70
    TING
    0.69
     conting
    0.68
    Activations Density 0.005%

    No Known Activations