© 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. 8274
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or measures in response to a situation or problem

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to taking action or implementing measures

    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
    ench
    -0.70
    inately
    -0.67
    Appearance
    -0.65
    orf
    -0.64
    ersion
    -0.63
    ocry
    -0.62
     Gloss
    -0.61
    rosis
    -0.61
     fame
    -0.61
    zzy
    -0.59
    POSITIVE LOGITS
     against
    1.05
     measures
    1.03
     steps
    1.01
     corrective
    0.96
     aimed
    0.93
     towards
    0.91
     undertaken
    0.91
     taken
    0.91
     Steps
    0.90
     ACTIONS
    0.89
    Activations Density 0.136%

    No Known Activations