© 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. 8-RES-JB
    11. 2466
    Prev
    Next
    INDEX
    Explanations

    verbs related to helping or contributing to a cause

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the action of helping or contributing towards a positive outcome

    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
     Tsukuyomi
    -0.68
     Procedure
    -0.68
    mails
    -0.64
     Goth
    -0.64
    ModLoader
    -0.62
     Malf
    -0.62
     Questions
    -0.62
     Canterbury
    -0.61
     Notting
    -0.60
     Comments
    -0.60
    POSITIVE LOGITS
     alleviate
    1.21
     strengthen
    1.18
     establish
    1.15
     perpetuate
    1.15
     amplify
    1.15
     facilitate
    1.13
     organize
    1.13
     relieve
    1.12
     promote
    1.12
     clarify
    1.11
    Activations Density 0.068%

    No Known Activations