© 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. 16964
    Prev
    Next
    INDEX
    Explanations

    political terms and actions related to decision-making, approval, and speculation

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating potential actions or outcomes

    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
    MpServer
    -0.72
    quickShipAvailable
    -0.71
     adolesc
    -0.71
     comprehension
    -0.71
    emetery
    -0.68
     occurred
    -0.66
     Kills
    -0.65
    Cor
    -0.65
    76561
    -0.65
    Rain
    -0.64
    POSITIVE LOGITS
     retaliate
    1.23
     balk
    1.21
     lose
    1.19
     argue
    1.18
     veto
    1.18
     decide
    1.15
     prefer
    1.12
     reap
    1.12
     pursue
    1.11
     gladly
    1.11
    Activations Density 0.233%

    No Known Activations