© 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. 8-RES-JB
    11. 19282
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs related to asking for or offering help

    oai_token-act-pair · gpt-3.5-turbo

    requests 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 @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.77
    ULAR
    -0.73
     ILCS
    -0.70
    BuyableInstoreAndOnline
    -0.66
     Ago
    -0.66
    bidden
    -0.65
    ASED
    -0.64
    edIn
    -0.63
     juven
    -0.62
    ternity
    -0.62
    POSITIVE LOGITS
     cope
    1.26
     achieve
    1.13
     navigate
    1.09
     organize
    1.08
     improve
    1.07
     solve
    1.06
     communicate
    1.05
     survive
    1.04
     resolve
    1.03
     formulate
    1.02
    Activations Density 0.184%

    No Known Activations