© 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. 7028
    Prev
    Next
    INDEX
    Explanations

    sequences of characters that don't form intelligible words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    elements of the Cyrillic alphabet

    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
     Clover
    -0.81
     apex
    -0.77
    agonist
    -0.76
    icles
    -0.75
    arton
    -0.75
    eatures
    -0.75
    aminer
    -0.74
    combe
    -0.73
    illary
    -0.71
    yrus
    -0.70
    POSITIVE LOGITS
    ÑĤ
    1.65
    д
    1.63
    м
    1.62
    к
    1.58
    Ñ
    1.55
    н
    1.54
    ÑĢ
    1.53
    Ð
    1.51
    Ñı
    1.46
    л
    1.44
    Activations Density 0.021%

    No Known Activations