© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 11525
    Prev
    Next
    INDEX
    Explanations

    instances of the word "yy" or "rr"

    oai_token-act-pair · gpt-3.5-turbo

    repeated vowel or consonant sequences, often indicative of informal or exaggerated expressions in text

    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
     distilled
    -0.85
     boiled
    -0.70
     boils
    -0.69
    otom
    -0.68
     kios
    -0.65
     vending
    -0.64
     ven
    -0.63
     Pers
    -0.63
     pav
    -0.61
     failure
    -0.61
    POSITIVE LOGITS
    hhhh
    1.11
    yy
    1.06
    aaaa
    1.06
    hh
    1.02
    ymm
    0.99
    hhh
    0.98
    AAA
    0.96
    AAAA
    0.96
    aaa
    0.95
    orld
    0.88
    Activations Density 0.015%

    No Known Activations