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

    Neuronpedia

    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. 15624
    Prev
    Next
    INDEX
    Explanations

    specific words or phrases related to social media activities or shares

    oai_token-act-pair · gpt-3.5-turbo

    references to social media engagement metrics like "shares."

    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
    aker
    -0.66
     leaf
    -0.64
     kit
    -0.63
     sequence
    -0.63
     flowering
    -0.62
     goalt
    -0.60
    ev
    -0.59
     Hansen
    -0.59
     treatment
    -0.59
     pitching
    -0.58
    POSITIVE LOGITS
     SHARES
    4.34
    SAN
    1.13
    20439
    1.07
    Shares
    1.06
     VIDEOS
    1.03
     Shares
    1.03
     IMAGES
    0.95
     ILCS
    0.92
    76561
    0.92
     GOODMAN
    0.92
    Activations Density 0.010%

    No Known Activations