© 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. 5643
    Prev
    Next
    INDEX
    Explanations

    specific named entities, potentially related to government, organizations, or locations

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the."

    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
    bg
    -0.68
    ictionary
    -0.62
    âĢij
    -0.61
    afe
    -0.61
    poke
    -0.61
    leeve
    -0.60
    eno
    -0.60
    ceive
    -0.60
    iffe
    -0.59
    aba
    -0.59
    POSITIVE LOGITS
     latter
    1.16
     largest
    1.09
     aforementioned
    1.05
     biggest
    1.04
     same
    1.04
     earliest
    1.02
     longest
    1.01
     smallest
    1.00
     strongest
    1.00
     oldest
    1.00
    Activations Density 1.766%

    No Known Activations