© 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. 4-RES-JB
    11. 388
    Prev
    Next
    INDEX
    Explanations

    texts related to making promises or commitments

    oai_token-act-pair · gpt-3.5-turbo

    words related to urging, requesting, or promoting actions

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

    No Comments

    Negative Logits
     Craw
    -0.68
    hack
    -0.66
    æѦ
    -0.64
    Poké
    -0.63
     Hollow
    -0.61
     Dortmund
    -0.60
     Dug
    -0.60
     Oval
    -0.59
    Buzz
    -0.58
    ynam
    -0.56
    POSITIVE LOGITS
    agree
    0.84
    iment
    0.82
     beware
    0.80
     mercy
    0.79
    haps
    0.79
    iments
    0.79
    ingly
    0.78
     modesty
    0.78
    soever
    0.77
     waive
    0.77
    Activations Density 0.252%

    No Known Activations