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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20292
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and their activities

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or teams and their dynamics

    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
    ensor
    -0.64
     oneself
    -0.62
    uggest
    -0.62
    omething
    -0.58
     Canaver
    -0.57
     extrad
    -0.55
     Hogan
    -0.54
     lett
    -0.53
    leep
    -0.53
    ync
    -0.52
    POSITIVE LOGITS
    mates
    1.87
     mates
    1.61
    mate
    1.38
     counterparts
    1.20
     mate
    1.11
     brethren
    1.05
     colleagues
    1.02
    members
    0.99
    men
    0.97
     partners
    0.96
    Activations Density 0.241%

    No Known Activations