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

    Neuronpedia

    Jacobian LensNEW
    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. 1688
    Prev
    Next
    INDEX
    Explanations

    specific instructions or commands related to using technology like software tools and scripts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "use" and related usage instructions

    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
     Mysteries
    -0.62
    Ń·
    -0.62
     behold
    -0.61
     nerv
    -0.61
     undertaking
    -0.61
    inois
    -0.60
     Bounty
    -0.57
     Buffett
    -0.56
     promulg
    -0.56
    cffffcc
    -0.56
    POSITIVE LOGITS
    fully
    1.15
    FUL
    1.10
    full
    1.02
    ful
    0.86
    fulness
    0.85
     sparing
    0.79
     tools
    0.79
     condoms
    0.76
     shortcuts
    0.74
     levers
    0.73
    Activations Density 0.086%

    No Known Activations