© 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. 11665
    Prev
    Next
    INDEX
    Explanations

    news sources and publications

    oai_token-act-pair · gpt-3.5-turbo

    references to news outlets and media sources

    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
    akespe
    -0.66
    ---------------
    -0.64
    itars
    -0.63
     sucker
    -0.61
     rebuilt
    -0.58
     rinse
    -0.58
     hump
    -0.57
    wikipedia
    -0.57
     pardon
    -0.56
     carp
    -0.56
    POSITIVE LOGITS
     Magazine
    1.18
     magazine
    1.11
    Magazine
    1.07
     News
    1.04
     contributor
    1.03
     Editorial
    1.02
     columnist
    0.98
     reporter
    0.98
     newspaper
    0.94
     Coverage
    0.94
    Activations Density 0.179%

    No Known Activations