© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17889
    Prev
    Next
    INDEX
    Explanations

    Medical terms and conditions

    oai_token-act-pair · gpt-3.5-turbo

    specific medical and legal terminology or concepts

    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
     whe
    -0.54
    udeb
    -0.51
     behold
    -0.47
     neut
    -0.47
     waning
    -0.46
    ¯
    -0.44
    天
    -0.43
    votes
    -0.42
     mush
    -0.42
     sab
    -0.42
    POSITIVE LOGITS
    hower
    0.66
    ashtra
    0.58
     Lives
    0.58
     Lobby
    0.56
     Advice
    0.55
     Lines
    0.55
    ulhu
    0.54
     Rates
    0.54
     Ratio
    0.54
     Affairs
    0.53
    Activations Density 0.882%

    No Known Activations