© 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. 3-RES-JB
    11. 18343
    Prev
    Next
    INDEX
    Explanations

    references to the word "Gren" and potentially health-related information like syndromes

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Gren" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stakes
    -0.78
     +/-
    -0.76
     Wiley
    -0.76
    áµ
    -0.73
     Subtle
    -0.68
     CNS
    -0.67
    CV
    -0.66
     CPC
    -0.65
    DNA
    -0.64
    1016
    -0.64
    POSITIVE LOGITS
    adier
    1.25
    fell
    1.02
    ecast
    0.96
    adel
    0.91
    auld
    0.88
    lette
    0.86
     Gren
    0.86
    emouth
    0.82
    ilit
    0.82
    heed
    0.82
    Activations Density 0.009%

    No Known Activations