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. 2-RES-JB
    6. 22883
    Prev
    Next
    INDEX
    Explanations

    phrases indicating partnerships or collaborations between entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "partnered" and its variations, indicating collaborations or alliances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esa
    -0.83
    esan
    -0.81
    thur
    -0.74
    mong
    -0.70
    she
    -0.70
    sburg
    -0.70
    topic
    -0.68
    seekers
    -0.68
     magnitude
    -0.67
    handler
    -0.65
    POSITIVE LOGITS
     partnered
    0.82
     prominently
    0.76
     commissioned
    0.72
     teamed
    0.71
     collaborated
    0.70
    inav
    0.70
    âĸ¬âĸ¬
    0.69
    river
    0.69
     digitally
    0.68
    nesday
    0.68
    Activations Density 0.026%

    No Known Activations