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. 7-RES-JB
    6. 14806
    Prev
    Next
    INDEX
    Explanations

    well wishes and expressions of good luck in messages

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing well-wishes and positive sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Churchill
    -0.63
     rehabilit
    -0.62
    SPONSORED
    -0.60
     halfway
    -0.59
    lishes
    -0.59
     midway
    -0.59
     reservoirs
    -0.57
     telesc
    -0.56
     myth
    -0.56
     vault
    -0.55
    POSITIVE LOGITS
    hesda
    0.79
     condolences
    0.76
    abee
    0.76
    bye
    0.76
     congr
    0.75
    EEE
    0.74
    rely
    0.73
    rick
    0.73
     amen
    0.73
    RIP
    0.70
    Activations Density 0.305%

    No Known Activations