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. 4583
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences that mention a specific word ending in 'il'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "il" in various contexts

    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
    Ħ¢
    -0.86
    ĪĴ
    -0.86
    ĵĺ
    -0.85
    -+-+
    -0.84
    ĸļ
    -0.83
    ©¶æ¥µ
    -0.73
    reme
    -0.71
    ¥ŀ
    -0.71
    ij士
    -0.70
    resy
    -0.70
    POSITIVE LOGITS
    ted
    1.01
    uvian
    1.01
     Nadu
    0.96
    aments
    0.95
    ocated
    0.95
    ibrary
    0.95
    ibr
    0.94
    uminati
    0.90
    ution
    0.89
    utive
    0.89
    Activations Density 0.024%

    No Known Activations