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. 14064
    Prev
    Next
    INDEX
    Explanations

    descriptions of things being concentrated in a particular place or group

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "concentrated" or its variations, indicating focus or accumulation

    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
    named
    -0.77
    ne
    -0.75
    quel
    -0.74
    conduct
    -0.71
    posted
    -0.71
    anne
    -0.70
    look
    -0.70
    aired
    -0.69
    clad
    -0.68
    him
    -0.68
    POSITIVE LOGITS
     concentrated
    0.91
     concentration
    0.88
     concent
    0.77
     concentrating
    0.77
     concentrate
    0.74
    ency
    0.74
     Concent
    0.73
    iple
    0.73
    herry
    0.73
     juices
    0.72
    Activations Density 0.022%

    No Known Activations