© 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. 3-RES-JB
    6. 12267
    Prev
    Next
    INDEX
    Explanations

    words related to concepts that are difficult to understand or imagine

    oai_token-act-pair · gpt-3.5-turbo

    terms related to comprehension and understanding

    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
    udeb
    -0.68
     compuls
    -0.68
     bye
    -0.67
     photoc
    -0.64
     postal
    -0.64
     redistributed
    -0.62
     regist
    -0.60
    ItemImage
    -0.60
     Antar
    -0.59
    fighting
    -0.59
    POSITIVE LOGITS
    athom
    1.12
    ulous
    0.93
    ibly
    0.90
    ierrez
    0.83
    ilk
    0.82
    redible
    0.81
    ilo
    0.79
     "$:/
    0.79
    dn
    0.78
    illion
    0.78
    Activations Density 0.011%

    No Known Activations