Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 8309
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or acknowledgment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and appreciation

    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
     Became
    -0.70
     lest
    -0.69
     detonated
    -0.68
    orius
    -0.67
    arde
    -0.67
    agame
    -0.67
    udo
    -0.66
    enium
    -0.66
    soever
    -0.66
    ringe
    -0.64
    POSITIVE LOGITS
     patronage
    1.13
     assistance
    1.13
     generosity
    1.12
     encouragement
    1.11
     patience
    1.08
     kindness
    1.06
     efforts
    1.01
     contribution
    1.01
     generous
    1.00
     dedication
    1.00
    Activations Density 0.132%

    No Known Activations