© 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. 16446
    Prev
    Next
    INDEX
    Explanations

    names of artists and entertainers

    oai_token-act-pair · gpt-3.5-turbo

    references to specific media titles or names

    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
     employer
    -0.62
     complying
    -0.61
    insured
    -0.61
     insurer
    -0.58
     subsistence
    -0.58
     employers
    -0.57
    hower
    -0.56
     labour
    -0.56
     Employ
    -0.55
     administr
    -0.55
    POSITIVE LOGITS
     cinematic
    0.83
     soundtrack
    0.71
     genre
    0.70
     Lovecraft
    0.67
     comedic
    0.66
     tv
    0.66
    Episode
    0.64
    series
    0.64
    Marvel
    0.64
     premie
    0.64
    Activations Density 3.957%

    No Known Activations