© 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. 9-RES-JB
    11. 9924
    Prev
    Next
    INDEX
    Explanations

    phrases related to referring a matter or seeking assistance

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating relationships or purposes related to actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ouse
    -0.76
     ®
    -0.72
     Asked
    -0.69
    deen
    -0.67
    beat
    -0.67
    Dutch
    -0.67
    facebook
    -0.66
    edin
    -0.66
    orie
    -0.66
    Fle
    -0.66
    POSITIVE LOGITS
     assistance
    1.24
     guidance
    1.14
     inclusion
    1.13
     approval
    1.06
     reimbursement
    1.05
     consideration
    1.03
     redress
    1.03
    geries
    1.02
     advice
    1.02
     clarification
    1.01
    Activations Density 0.204%

    No Known Activations