© 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. 10-RES-JB
    11. 2279
    Prev
    Next
    INDEX
    Explanations

    verbs related to reaching conclusions or agreements

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "come to" in various contexts

    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
    vich
    -0.73
    going
    -0.63
    hur
    -0.63
    bis
    -0.62
    sports
    -0.62
     incoming
    -0.62
     postponed
    -0.61
     spilled
    -0.60
    prem
    -0.60
    ¼
    -0.59
    POSITIVE LOGITS
     grips
    1.31
     fruition
    1.11
     realise
    1.03
     realize
    1.00
     rely
    0.97
     blows
    0.94
     terms
    0.93
     prominence
    0.89
     dominate
    0.87
     conclusions
    0.85
    Activations Density 0.041%

    No Known Activations