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. 10609
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names of places, particularly focusing on names ending in 'ing'

    oai_token-act-pair · gpt-3.5-turbo

    present participles and gerunds, specifically those that relate to actions or states

    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
    nery
    -0.77
    ieving
    -0.75
    itism
    -0.75
    ably
    -0.74
    ihar
    -0.73
    pering
    -0.71
    bal
    -0.71
    iness
    -0.71
    igning
    -0.70
    hooting
    -0.70
    POSITIVE LOGITS
    tons
    1.36
    ham
    0.98
    HAM
    0.95
    redients
    0.94
     Sands
    0.91
    ton
    0.88
    uez
    0.86
    allery
    0.81
    bird
    0.81
     Stones
    0.79
    Activations Density 0.133%

    No Known Activations