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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 21920
    Prev
    Next
    INDEX
    Explanations

    instances where individuals are considering or actually deciding to join something

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of joining something or becoming part of a group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    framework
    -0.67
    bach
    -0.66
    icz
    -0.65
    ibia
    -0.65
    intendent
    -0.64
    inav
    -0.63
    bane
    -0.63
    prototype
    -0.62
    merce
    -0.61
    issa
    -0.61
    POSITIVE LOGITS
     forces
    1.25
     Forces
    0.95
     ranks
    0.89
    TAIN
    0.84
     hands
    0.75
     them
    0.74
    OOL
    0.71
     us
    0.68
     voluntarily
    0.66
     together
    0.66
    Activations Density 0.039%

    No Known Activations