© 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. 10140
    Prev
    Next
    INDEX
    Explanations

    information about the size, rankings, or order of things

    oai_token-act-pair · gpt-3.5-turbo

    references to large quantities or significant entities in various contexts

    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
     Wilde
    -0.70
     interchange
    -0.66
     orally
    -0.66
     Unch
    -0.64
     Koen
    -0.63
     administered
    -0.61
     disbel
    -0.60
     KL
    -0.59
     caps
    -0.58
     cis
    -0.57
    POSITIVE LOGITS
    tenance
    1.38
    lihood
    1.12
    alyst
    1.10
    amental
    1.09
    ior
    1.08
    erie
    1.08
    ousand
    1.05
    istance
    1.04
    urance
    1.03
    eting
    1.03
    Activations Density 0.318%

    No Known Activations