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. 8-RES-JB
    6. 5389
    Prev
    Next
    INDEX
    Explanations

    age numbers

    oai_token-act-pair · gpt-3.5-turbo

    numeric values associated with ages

    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
     constitu
    -0.69
    izens
    -0.61
    ebin
    -0.61
    access
    -0.59
     dictators
    -0.58
     manifold
    -0.57
     stabilization
    -0.57
     vibrations
    -0.56
     âī
    -0.56
    oids
    -0.56
    POSITIVE LOGITS
    %,
    0.91
     Rue
    0.82
    %-
    0.81
    yo
    0.78
    %;
    0.78
    cm
    0.73
    rd
    0.73
    th
    0.73
    nd
    0.72
     Downing
    0.70
    Activations Density 0.056%

    No Known Activations