Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 199
    Prev
    Next
    INDEX
    Explanations

    words related to management and control

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "manage" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çīĪ
    -0.83
    Magikarp
    -0.76
    PU
    -0.75
    ilings
    -0.75
    ode
    -0.73
    reek
    -0.73
     Vide
    -0.72
    qt
    -0.70
     Mehran
    -0.69
    ittal
    -0.68
    POSITIVE LOGITS
    uate
    0.80
    ahime
    0.79
     allocation
    0.75
     complexity
    0.73
     managing
    0.73
     affairs
    0.72
     manage
    0.71
    urally
    0.68
     oversight
    0.68
    urable
    0.68
    Activations Density 0.031%

    No Known Activations