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. 12-RES-JB
    6. 15185
    Prev
    Next
    INDEX
    Explanations

    verbs related to performing actions or tasks, especially highlighting the aspect of doing a particular action

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of the word "perform" along with various forms of performing, particularly in relation to duties, sexual acts, and other contexts of action or execution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ener
    -0.75
    inki
    -0.74
    issue
    -0.71
    izons
    -0.71
    Nusra
    -0.68
    meier
    -0.66
    starter
    -0.65
    unity
    -0.64
    moil
    -0.64
     issue
    -0.62
    POSITIVE LOGITS
     miracles
    1.16
     stunts
    1.09
     feats
    1.08
     tasks
    1.04
     CPR
    0.98
     tricks
    0.93
     duties
    0.92
     surgeries
    0.92
     rituals
    0.91
     chores
    0.89
    Activations Density 0.171%

    No Known Activations