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. 8-RES-JB
    6. 18985
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication or conversation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of apologies or expressions of regret

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.88
    essential
    -0.71
    animate
    -0.65
    capacity
    -0.64
    existence
    -0.64
    utic
    -0.63
    die
    -0.63
    atile
    -0.62
    activation
    -0.61
    competitive
    -0.61
    POSITIVE LOGITS
     retweet
    0.98
     apologized
    0.97
     emailed
    0.93
     thanked
    0.92
     rhet
    0.87
     tweeted
    0.87
     commenters
    0.85
     summarized
    0.80
     apologised
    0.79
     commented
    0.78
    Activations Density 0.669%

    No Known Activations