© 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. 3-RES-JB
    11. 12838
    Prev
    Next
    INDEX
    Explanations

    phrases marked by a unique symbol

    oai_token-act-pair · gpt-3.5-turbo

    instances of the symbol sequence "âĢĵ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.86
    ient
    -0.72
    orts
    -0.72
     proportion
    -0.71
     strugg
    -0.71
     nurs
    -0.70
    lene
    -0.70
     overpowered
    -0.70
    zhou
    -0.69
     metic
    -0.69
    POSITIVE LOGITS
    ––
    1.41
    ————
    0.95
    âĸº
    0.94
    ——
    0.88
    Tenn
    0.82
    ————————————————
    0.81
    _-
    0.80
    ————————
    0.79
    Maria
    0.73
    âĢķ
    0.71
    Activations Density 0.114%

    No Known Activations