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. 1664
    Prev
    Next
    INDEX
    Explanations

    terms related to management or control in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "manage" and its variations, indicating a focus on management concepts

    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
    çīĪ
    -0.82
    PU
    -0.79
    reek
    -0.78
    icipated
    -0.76
    Magikarp
    -0.72
    qt
    -0.70
    ilings
    -0.69
    asus
    -0.66
    PLA
    -0.66
    raid
    -0.66
    POSITIVE LOGITS
    ahime
    0.85
     manage
    0.75
     managing
    0.74
    ité
    0.73
    uate
    0.72
    izational
    0.72
    urable
    0.71
    vier
    0.69
    ices
    0.69
     manages
    0.69
    Activations Density 0.017%

    No Known Activations