© 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. 8-RES-JB
    11. 1286
    Prev
    Next
    INDEX
    Explanations

    phrases ending with the punctuation "Ļ"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character 'Ļ' in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myster
    -0.71
     scattering
    -0.71
    undown
    -0.68
     rotating
    -0.68
     mosqu
    -0.66
     clipping
    -0.63
     blending
    -0.61
     alternating
    -0.61
     Allied
    -0.61
     succession
    -0.61
    POSITIVE LOGITS
    ï¸ı
    0.92
    ebook
    0.88
    ese
    0.81
    own
    0.77
    self
    0.77
    amaz
    0.76
    abad
    0.75
    #$
    0.75
    mean
    0.74
     deserve
    0.73
    Activations Density 0.244%

    No Known Activations