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. 10-RES-JB
    6. 2039
    Prev
    Next
    INDEX
    Explanations

    instances related to people and their actions in various scenarios, such as traveling, playing, living, and being involved in legal matters

    oai_token-act-pair · gpt-3.5-turbo

    references to people, migration, or events involving groups and significant actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    `.
    -0.76
    ESE
    -0.72
    ":-
    -0.65
    ECA
    -0.62
    >[
    -0.60
    enne
    -0.59
    retty
    -0.58
    /-
    -0.57
    DL
    -0.57
    ','
    -0.57
    POSITIVE LOGITS
     has
    1.06
     appears
    1.02
     disappears
    1.02
     was
    0.99
     expires
    0.97
     violates
    0.97
     enters
    0.97
     receives
    0.95
     survives
    0.93
     earns
    0.92
    Activations Density 0.591%

    No Known Activations