© 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. 594
    Prev
    Next
    INDEX
    Explanations

    instances where something is mentioned, typically to emphasize importance or highlight information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mention" in a variety of contexts

    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
    sett
    -0.77
    ¯¯¯¯¯¯¯¯
    -0.74
     sled
    -0.72
    uilt
    -0.69
    orneys
    -0.68
     Drag
    -0.68
     waged
    -0.66
    gamer
    -0.66
     millenn
    -0.66
    ¯¯
    -0.65
    POSITIVE LOGITS
     mentions
    0.97
     mentioning
    0.96
     mention
    0.92
    lihood
    0.88
    fulness
    0.84
    ibility
    0.77
    cliffe
    0.77
     aloud
    0.76
    lessness
    0.76
    lessly
    0.75
    Activations Density 0.020%

    No Known Activations