© 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. 22937
    Prev
    Next
    INDEX
    Explanations

    terms related to computer programming tasks and instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms indicating the completion of tasks or installations

    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
    Cole
    -0.71
     Townsend
    -0.71
    umber
    -0.67
     Cole
    -0.64
     hashtag
    -0.63
    earth
    -0.62
    sun
    -0.61
    Rush
    -0.60
     widow
    -0.60
    liners
    -0.60
    POSITIVE LOGITS
     finished
    0.86
     Config
    0.84
     satisfied
    0.84
    Setup
    0.84
    Config
    0.82
     desired
    0.82
    Congratulations
    0.81
     compr
    0.78
     completed
    0.78
     configured
    0.76
    Activations Density 0.325%

    No Known Activations