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. 13533
    Prev
    Next
    INDEX
    Explanations

    scientific terms or names related to astronomy

    oai_token-act-pair · gpt-3.5-turbo

    suffixes and word endings that are common in various contexts, particularly focusing on 'ck', 'ren', and other recurring letter patterns

    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
    owship
    -0.70
    itu
    -0.69
    oru
    -0.61
     Neighbor
    -0.60
    asury
    -0.58
     repay
    -0.58
    advertisement
    -0.57
     Avalon
    -0.57
     parasitic
    -0.57
    pay
    -0.56
    POSITIVE LOGITS
    theless
    0.75
    uese
    0.73
    berra
    0.66
    ried
    0.63
    opolis
    0.62
    auld
    0.62
    lation
    0.58
    WER
    0.58
    Discover
    0.58
    atron
    0.58
    Activations Density 0.249%

    No Known Activations