© 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. 10-RES-JB
    11. 799
    Prev
    Next
    INDEX
    Explanations

    mentions of people with a high following on social media

    oai_token-act-pair · gpt-3.5-turbo

    references to social media popularity and trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    juries
    -0.78
     Reduce
    -0.76
    adequ
    -0.75
     defic
    -0.74
     fails
    -0.72
    failed
    -0.72
     weakest
    -0.72
    worst
    -0.72
    dam
    -0.71
     Sorry
    -0.71
    POSITIVE LOGITS
     eagerly
    1.11
     enthusiastically
    1.09
     retweet
    1.09
     eager
    1.05
     dissemin
    1.03
     delighted
    0.95
     invitations
    0.95
     gossip
    0.95
     avid
    0.95
     admire
    0.94
    Activations Density 0.842%

    No Known Activations