© 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. 9-RES-JB
    11. 19735
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrast or a shift in focus

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating contrast or opposition in arguments

    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
    ãĤ¼ãĤ¦ãĤ¹
    -0.85
    $$$$
    -0.83
    pmwiki
    -0.79
    Woman
    -0.78
    ENG
    -0.76
    ãĤµ
    -0.74
    encia
    -0.73
    iphate
    -0.71
    ãĤ¨ãĥ«
    -0.70
    rolled
    -0.69
    POSITIVE LOGITS
     it
    1.06
     insofar
    1.02
     nevertheless
    0.95
     nonetheless
    0.95
     moreover
    0.90
     proponents
    0.86
     parallels
    0.83
     policymakers
    0.83
     acknowledging
    0.82
     empirical
    0.82
    Activations Density 0.497%

    No Known Activations