© 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. 4-RES-JB
    6. 20660
    Prev
    Next
    INDEX
    Explanations

    names of people, locations, and political terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of organizations, movements, or notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disg
    -0.71
     cov
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.67
     compe
    -0.67
     srfAttach
    -0.65
    è£
    -0.64
     surv
    -0.64
     symp
    -0.63
     respons
    -0.61
     remem
    -0.60
    POSITIVE LOGITS
    zbollah
    0.85
    Wiki
    0.75
    oÄŁan
    0.73
     Updated
    0.72
    oval
    0.71
    Skip
    0.70
    isoft
    0.68
    Hack
    0.68
    bitcoin
    0.67
     Recap
    0.65
    Activations Density 0.259%

    No Known Activations