© 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. 9-RES-JB
    11. 7327
    Prev
    Next
    INDEX
    Explanations

    detailed observations and measurements captured in images

    oai_token-act-pair · gpt-3.5-turbo

    references to visual data and measurements in scientific observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     boycot
    -0.73
     Rebell
    -0.73
     disliked
    -0.69
     pacif
    -0.65
    iquette
    -0.65
    advertising
    -0.64
    oiler
    -0.64
     Quit
    -0.63
     Masquerade
    -0.63
     circumstance
    -0.62
    POSITIVE LOGITS
    atellite
    0.92
     datasets
    0.90
     satellites
    0.89
     microsc
    0.86
     infrared
    0.86
     electron
    0.84
    metry
    0.82
    rared
    0.82
     wavelengths
    0.81
    atell
    0.81
    Activations Density 0.204%

    No Known Activations