© 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. 7-RES-JB
    11. 13690
    Prev
    Next
    INDEX
    Explanations

    keywords related to financial stability and instructions on standing strong

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions or instances of the word "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DX
    -0.68
    itans
    -0.66
    meet
    -0.64
    atten
    -0.62
    AMS
    -0.62
    asse
    -0.61
     incent
    -0.60
    SG
    -0.60
    Course
    -0.58
     Voters
    -0.58
    POSITIVE LOGITS
     thereby
    0.98
     consequently
    0.96
     thus
    0.96
     hence
    0.94
     therefore
    0.90
     vice
    0.89
     thence
    0.88
     then
    0.85
    rew
    0.82
     secondly
    0.82
    Activations Density 0.206%

    No Known Activations