© 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. 4-RES-JB
    11. 10353
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names or places, particularly variations of "Varanas" or "Varanasi"

    oai_token-act-pair · gpt-3.5-turbo

    references to the economist Varoufakis

    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
    insula
    -0.93
    ĨĴ
    -0.91
    ãĤ´ãĥ³
    -0.84
    anwhile
    -0.78
     Doodle
    -0.78
    creen
    -0.77
    ometimes
    -0.77
    æĸ¹
    -0.74
    éĹĺ
    -0.72
    ecake
    -0.72
    POSITIVE LOGITS
    args
    0.98
    ieties
    0.90
    anas
    0.87
    arak
    0.82
    izon
    0.82
    iously
    0.79
    iola
    0.79
    ise
    0.78
    ietal
    0.76
    issa
    0.76
    Activations Density 0.014%

    No Known Activations