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. 5-RES-JB
    6. 21637
    Prev
    Next
    INDEX
    Explanations

    mentions of large numbers such as quantities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to large population figures or quantities in millions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imen
    -0.80
    sonian
    -0.75
    krit
    -0.70
     Dating
    -0.69
    ifice
    -0.67
    cade
    -0.66
    nam
    -0.65
    anwhile
    -0.65
    alid
    -0.65
    emia
    -0.65
    POSITIVE LOGITS
     hectares
    1.11
     pounds
    1.01
     dollars
    0.99
     tonnes
    0.95
     yuan
    0.95
     acres
    0.95
     miles
    0.93
     yen
    0.93
     lbs
    0.93
     litres
    0.89
    Activations Density 0.063%

    No Known Activations