© 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. 10-RES-JB
    11. 20391
    Prev
    Next
    INDEX
    Explanations

    phrases related to social or political debates and discussions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include conditional statements or implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ļéĨĴ
    -0.78
    ãĤ´ãĥ³
    -0.74
    ãĤ¨ãĥ«
    -0.73
    VERTISEMENT
    -0.72
    Ě
    -0.69
    ğ
    -0.69
    quickShip
    -0.69
    Ė
    -0.69
    ē
    -0.69
    ă
    -0.69
    POSITIVE LOGITS
     then
    1.36
    then
    1.27
     surely
    1.21
     why
    1.19
     THEN
    1.09
     chances
    0.98
     maybe
    0.98
    why
    0.96
     shouldn
    0.93
     please
    0.92
    Activations Density 0.185%

    No Known Activations