© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 13728
    Prev
    Next
    INDEX
    Explanations

    references to the action of sharing something

    oai_token-act-pair · gpt-3.5-turbo

    words related to sharing and social media engagement

    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
     Majesty
    -0.69
     piping
    -0.64
     decre
    -0.63
     para
    -0.63
     acoustic
    -0.63
     overt
    -0.63
     audible
    -0.61
     Condition
    -0.60
     acts
    -0.58
    ̶
    -0.58
    POSITIVE LOGITS
    share
    4.30
    hare
    1.24
    SHARE
    1.10
    Share
    1.09
    sharing
    1.08
    shared
    0.98
     share
    0.97
    stock
    0.97
    Stock
    0.93
     IST
    0.93
    Activations Density 0.024%

    No Known Activations