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. 18533
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a call to action or a request for a specific action to be taken

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases or calls to action

    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
    VERTISEMENT
    -0.91
    ©¶æ¥µ
    -0.77
     âĶľâĶĢâĶĢ
    -0.67
    eah
    -0.66
    low
    -0.66
    rough
    -0.64
     Ãľ
    -0.63
     LX
    -0.63
    ãĤª
    -0.63
     Pend
    -0.62
    POSITIVE LOGITS
    erous
    1.01
     behalf
    0.96
    shore
    0.84
     reinforcements
    0.80
    etimes
    0.72
    reb
    0.72
     elders
    0.70
    unal
    0.69
    Downloadha
    0.68
     circulation
    0.68
    Activations Density 0.045%

    No Known Activations