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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 16075
    Prev
    Next
    INDEX
    Explanations

    verbs related to taking action or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    actions implying restriction or removal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    aned
    -0.70
    imentary
    -0.64
    luster
    -0.62
    pmwiki
    -0.59
    inis
    -0.58
    successfully
    -0.55
     impressed
    -0.55
     molded
    -0.55
    ombo
    -0.55
     predicting
    -0.55
    POSITIVE LOGITS
     Guantanamo
    0.89
     ASAP
    0.76
     them
    0.75
     him
    0.72
     whoever
    0.71
     DACA
    0.71
     Guant
    0.71
     Trident
    0.70
     all
    0.68
    xit
    0.67
    Activations Density 0.378%

    No Known Activations