© 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. 10-RES-JB
    11. 14063
    Prev
    Next
    INDEX
    Explanations

    instances where individuals are in need of help or assistance

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing the act of seeking assistance or help

    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
     ®
    -0.80
    sonian
    -0.77
    fleet
    -0.76
    gdala
    -0.76
    hops
    -0.74
    itect
    -0.73
    iltr
    -0.73
    Pub
    -0.70
    è¦ļéĨĴ
    -0.69
    mare
    -0.69
    POSITIVE LOGITS
     assistance
    1.17
     help
    1.17
     inspiration
    1.12
     mercy
    1.12
     approval
    1.06
     forgiveness
    1.05
     permission
    1.05
    gery
    1.05
     clarification
    1.05
     answers
    1.03
    Activations Density 0.210%

    No Known Activations