© 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. 4-RES-JB
    11. 12035
    Prev
    Next
    INDEX
    Explanations

    keywords related to causation or purpose

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating causation or consequence

    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
    ten
    -0.71
     Atkinson
    -0.68
    kick
    -0.63
     Williamson
    -0.62
    shit
    -0.62
     Freddie
    -0.61
     Serge
    -0.61
     Kelvin
    -0.61
    enta
    -0.61
    ter
    -0.60
    POSITIVE LOGITS
     guiActiveUn
    0.98
    forth
    0.89
    ãĤ´ãĥ³
    0.81
     convol
    0.78
     sidx
    0.78
    cedes
    0.74
    hiba
    0.74
     guiActive
    0.72
     forfe
    0.71
     conclud
    0.71
    Activations Density 0.010%

    No Known Activations