© 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. 20744
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific research findings

    oai_token-act-pair · gpt-3.5-turbo

    statements that present findings or evidence in the context of research

    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
    deal
    -0.87
    bart
    -0.86
    biz
    -0.84
    iciary
    -0.81
    adr
    -0.80
    é¾
    -0.79
    DragonMagazine
    -0.79
    ãĥĩ
    -0.78
    Guard
    -0.76
    Tank
    -0.76
    POSITIVE LOGITS
     genes
    0.97
     altering
    0.96
     prenatal
    0.95
     endogenous
    0.95
     ingestion
    0.94
     oxidative
    0.94
     epigen
    0.94
     correlations
    0.94
     correlation
    0.93
     cannabinoids
    0.93
    Activations Density 0.205%

    No Known Activations