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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 24539
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the necessity of making a decision or taking action

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to decision-making and actions taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orescence
    -0.80
    Merit
    -0.69
    ocry
    -0.62
    oulos
    -0.60
    Problem
    -0.60
    ayed
    -0.60
    quartered
    -0.59
    Reading
    -0.59
    nih
    -0.59
    luaj
    -0.58
    POSITIVE LOGITS
     somewhere
    1.07
     lest
    0.91
     manually
    0.87
     compromises
    0.84
     something
    0.83
     somew
    0.81
     harder
    0.79
     drastic
    0.78
     somehow
    0.78
     anew
    0.77
    Activations Density 0.276%

    No Known Activations