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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 21659
    Prev
    Next
    INDEX
    Explanations

    universities and locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific symbol or character that appear frequently in the text

    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
    ysis
    -0.81
    iple
    -0.74
     Berm
    -0.73
     Blu
    -0.72
     redes
    -0.72
     parted
    -0.70
    zzy
    -0.70
    ãĥ¼ãĥĨãĤ£
    -0.68
    oller
    -0.66
    iane
    -0.65
    POSITIVE LOGITS
    cases
    0.91
    advertising
    0.91
    micro
    0.87
    advertisement
    0.85
    specific
    0.85
    style
    0.81
    Pg
    0.80
    double
    0.79
    coll
    0.79
    craft
    0.78
    Activations Density 0.029%

    No Known Activations