© 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 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. 8-RES-JB
    11. 19349
    Prev
    Next
    INDEX
    Explanations

    phrases related to standout, impressive, or dominant performances in various contexts such as sports or work

    oai_token-act-pair · gpt-3.5-turbo

    references to athletic or artistic performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dispute
    -0.64
     bindings
    -0.63
     consortium
    -0.63
     fork
    -0.62
     jurisd
    -0.61
     craw
    -0.60
    ocol
    -0.60
     labyrinth
    -0.60
    conservancy
    -0.59
     Objects
    -0.58
    POSITIVE LOGITS
     offensively
    1.07
    ufact
    0.98
     defensively
    0.94
     athlet
    0.90
     elsewhere
    0.86
     Incarn
    0.84
     abroad
    0.84
     during
    0.82
     performances
    0.81
    BIP
    0.81
    Activations Density 0.300%

    No Known Activations