© 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. 0-RES-JB
    11. 4962
    Prev
    Next
    INDEX
    Explanations

    words related to providing assistance or support

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate assistance or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apsed
    -0.68
     utter
    -0.66
     absolute
    -0.65
     undefined
    -0.62
     yet
    -0.59
     extant
    -0.56
     unnamed
    -0.56
     unknown
    -0.55
     unre
    -0.55
    ilib
    -0.54
    POSITIVE LOGITS
     helps
    3.11
    helps
    2.21
     helped
    1.95
     improves
    1.85
     facilitates
    1.83
     enhances
    1.81
     encourages
    1.78
     strengthens
    1.78
     contributes
    1.71
     solves
    1.69
    Activations Density 0.014%

    No Known Activations