© 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. 2-RES-JB
    11. 5443
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences related to making a commitment or taking action towards a decision or course of action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "commit" and its variations, often in the context of actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ther
    -0.65
    sama
    -0.64
     Plat
    -0.64
    fml
    -0.63
    Fram
    -0.62
    phe
    -0.62
     Swiss
    -0.62
    ****************
    -0.61
    Controller
    -0.60
    atin
    -0.59
    POSITIVE LOGITS
     commit
    0.96
    commit
    0.92
     commits
    0.87
     committed
    0.83
     committing
    0.79
    ruction
    0.78
    lesh
    0.76
    uates
    0.76
    interstitial
    0.76
    utions
    0.75
    Activations Density 0.014%

    No Known Activations