© 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. 10-RES-JB
    11. 3108
    Prev
    Next
    INDEX
    Explanations

    instructions and steps written in a tutorial or guide

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to software installation and setup processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Years
    -0.72
    oids
    -0.69
    soType
    -0.68
    SPONSORED
    -0.67
    AFP
    -0.62
     Ashton
    -0.62
     satire
    -0.61
    NEWS
    -0.60
    archives
    -0.58
    wives
    -0.58
    POSITIVE LOGITS
     finished
    1.17
     Finished
    1.06
    Congratulations
    1.05
     completed
    1.04
     satisfied
    1.04
    itialized
    1.00
     Completed
    0.97
     successfully
    0.97
     completes
    0.97
     setup
    0.97
    Activations Density 0.197%

    No Known Activations