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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 15748
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to publicity or promotion

    oai_token-act-pair · gpt-3.5-turbo

    references to publicity and its various aspects

    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
    tein
    -0.90
    artment
    -0.67
    tre
    -0.67
    inite
    -0.65
    osite
    -0.64
     Republic
    -0.63
    cise
    -0.58
    audi
    -0.58
    OTS
    -0.58
     heartbeat
    -0.57
    POSITIVE LOGITS
     Incarn
    0.83
    seekers
    0.81
    quickShipAvailable
    0.81
    worthy
    0.80
     publicity
    0.79
    seeking
    0.78
     surrounding
    0.76
    arily
    0.76
    isSpecialOrderable
    0.75
    ously
    0.74
    Activations Density 0.112%

    No Known Activations