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. 0-RES-JB
    6. 24471
    Prev
    Next
    INDEX
    Explanations

    instances of the word "joined"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "joined" to indicate associations or collaborations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odor
    -0.69
    imate
    -0.61
     ASAP
    -0.58
    animate
    -0.58
    ateral
    -0.58
    imize
    -0.57
    umph
    -0.57
     authenticity
    -0.57
     Siber
    -0.56
    ulent
    -0.56
    POSITIVE LOGITS
     joined
    3.49
     joins
    2.13
    joined
    2.02
     join
    1.93
     joining
    1.92
     teamed
    1.60
     participated
    1.53
     Joined
    1.51
     rejo
    1.47
    joining
    1.47
    Activations Density 0.016%

    No Known Activations