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. 11-RES-JB
    6. 3024
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or requests for action at the end of a message

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to gratitude and subscription acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UGE
    -0.56
     helicop
    -0.54
    naires
    -0.54
     theoret
    -0.53
     virginity
    -0.53
     shortened
    -0.52
     Helic
    -0.52
     Dough
    -0.51
     Tarant
    -0.51
    irlf
    -0.50
    POSITIVE LOGITS
     subscribing
    0.71
    scribe
    0.65
    entimes
    0.65
    Reviewer
    0.64
    etsy
    0.57
    Cos
    0.56
    interstitial
    0.56
    pload
    0.55
    ]);
    0.54
    knit
    0.54
    Activations Density 0.020%

    No Known Activations