© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 10172
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a requirement or obligation to do something specific

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Emerging
    -0.73
     Lif
    -0.72
    interstitial
    -0.66
     Ideal
    -0.65
     Info
    -0.64
     Ends
    -0.62
     Rust
    -0.61
     Milky
    -0.60
     Nights
    -0.59
     Gulf
    -0.59
    POSITIVE LOGITS
     rely
    1.35
     endure
    1.31
     contend
    1.30
     wait
    1.29
     worry
    1.22
     reckon
    1.20
     fend
    1.18
     resort
    1.15
     cope
    1.14
     compete
    1.11
    Activations Density 0.091%

    No Known Activations