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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 16510
    Prev
    Next
    INDEX
    Explanations

    phrases related to various forms of needing help or assistance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a need for 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
    nown
    -0.79
    otypes
    -0.77
    acebook
    -0.74
    ocry
    -0.73
    pecting
    -0.73
    azar
    -0.72
    asionally
    -0.71
    viously
    -0.67
    RANT
    -0.67
    ears
    -0.66
    POSITIVE LOGITS
     refres
    1.12
     help
    1.04
     clarification
    1.02
     urgently
    1.01
     HELP
    0.99
     reinforcement
    0.94
     reinforcements
    0.94
     guidance
    0.91
     boost
    0.90
     reminder
    0.90
    Activations Density 0.197%

    No Known Activations