© 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. 13615
    Prev
    Next
    INDEX
    Explanations

    words with diacritical marks or special characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or sequence of letters in the text

    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
     fortun
    -0.75
    uyomi
    -0.67
    istically
    -0.67
    pert
    -0.67
    ————————
    -0.65
     reviewer
    -0.64
     Marketable
    -0.64
    pend
    -0.63
     resil
    -0.63
     compe
    -0.63
    POSITIVE LOGITS
    Äį
    1.00
    kg
    0.88
    insk
    0.83
    rium
    0.79
    okers
    0.79
    rez
    0.78
    ijn
    0.78
    ka
    0.78
    ovo
    0.77
    nen
    0.76
    Activations Density 0.004%

    No Known Activations