© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 5052
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or commands

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating potential actions or obligations

    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
     Moroc
    -0.53
    luster
    -0.53
     Lon
    -0.50
    Gall
    -0.49
    Base
    -0.48
     Fern
    -0.47
    Spot
    -0.47
    Thankfully
    -0.46
    EO
    -0.46
     Jou
    -0.45
    POSITIVE LOGITS
     merge
    0.89
     migrate
    0.85
     apologise
    0.83
     terminate
    0.81
     unite
    0.80
     survive
    0.80
     deceive
    0.80
     proceed
    0.79
     penetrate
    0.79
     stabilize
    0.78
    Activations Density 0.463%

    No Known Activations