© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10008
    Prev
    Next
    INDEX
    Explanations

    words related to expressing gratitude or appreciation

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks that denote strong emotions or emphasis

    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
     plaus
    -0.80
     predec
    -0.74
     attrition
    -0.73
    ensibly
    -0.73
     casualty
    -0.73
    iosyncr
    -0.72
     insurgency
    -0.72
     precip
    -0.72
     evade
    -0.72
     defe
    -0.71
    POSITIVE LOGITS
     Thank
    1.81
     THANK
    1.62
     Thanks
    1.52
     Congratulations
    1.52
    Thank
    1.48
     Truly
    1.35
     Hopefully
    1.34
     Especially
    1.30
     Lastly
    1.26
     Highly
    1.25
    Activations Density 0.339%

    No Known Activations