© 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. 7-RES-JB
    11. 21207
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving advice or instructions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate obligation or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lambert
    -0.68
    closed
    -0.64
     Rust
    -0.63
     Globe
    -0.63
     Emerging
    -0.60
    Recommended
    -0.60
    vironment
    -0.60
    lip
    -0.58
     Lis
    -0.58
     Baird
    -0.57
    POSITIVE LOGITS
     rely
    1.06
     wait
    1.05
     abide
    0.99
     obey
    0.97
     remind
    0.96
     prove
    0.95
     toe
    0.92
     comply
    0.92
     contend
    0.92
     beware
    0.91
    Activations Density 0.103%

    No Known Activations