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. 11-RES-JB
    6. 19423
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration or joint action involving multiple people

    oai_token-act-pair · gpt-3.5-turbo

    instances of collaborative actions or associations among individuals

    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
    izu
    -0.69
    Detailed
    -0.67
    itution
    -0.65
    ãĥİ
    -0.64
    ãĤ¨ãĥ«
    -0.64
    cms
    -0.63
    olation
    -0.62
    CPU
    -0.60
    uncture
    -0.60
    Report
    -0.60
    POSITIVE LOGITS
     fellow
    1.22
     others
    1.19
     his
    1.12
     other
    1.09
     colleagues
    1.08
     colleague
    1.00
     Associates
    0.96
     several
    0.95
     teammate
    0.93
     dozens
    0.92
    Activations Density 0.144%

    No Known Activations