© 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. 2-RES-JB
    11. 17088
    Prev
    Next
    INDEX
    Explanations

    phrases with the pattern "âĢĻ" followed by a number as a token

    oai_token-act-pair · gpt-3.5-turbo

    instances of a particular character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imitation
    -0.71
     carbohyd
    -0.67
    arios
    -0.65
    raviolet
    -0.64
    ramid
    -0.63
     pyramid
    -0.63
    iage
    -0.62
    wana
    -0.62
     convenience
    -0.62
     XT
    -0.61
    POSITIVE LOGITS
    女
    1.03
    Ļ
    0.96
    ï¸ı
    0.92
    İ
    0.87
    Ùħ
    0.86
    Ľ
    0.85
    ı
    0.84
    Ķ
    0.82
    ļ
    0.82
    ð
    0.81
    Activations Density 0.488%

    No Known Activations