© 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 EvalsExportsinterp-engineNEWAPI 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. 23422
    Prev
    Next
    INDEX
    Explanations

    references to different groups, organizations, or entities

    oai_token-act-pair · gpt-3.5-turbo

    the word "also" and variations in its context to indicate addition or emphasis

    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
     EVEN
    -0.71
     even
    -0.65
    lore
    -0.64
     ANY
    -0.63
    uble
    -0.62
    anon
    -0.61
    even
    -0.61
     moreover
    -0.61
    izont
    -0.60
    only
    -0.58
    POSITIVE LOGITS
     contributed
    0.84
     implicated
    0.81
     participated
    0.80
     affected
    0.78
     impacted
    0.77
     benefited
    0.77
     weighed
    0.76
     reportedly
    0.74
     criticised
    0.74
     confir
    0.73
    Activations Density 0.116%

    No Known Activations