© 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. 11375
    Prev
    Next
    INDEX
    Explanations

    text related to political events or communications

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to government opposition and requests for action

    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
     gadgets
    -0.80
     maths
    -0.80
     shrug
    -0.76
     meanwhile
    -0.74
     shrugged
    -0.73
     pric
    -0.72
     woo
    -0.71
     sweets
    -0.71
    isers
    -0.70
     tack
    -0.69
    POSITIVE LOGITS
     Defendant
    1.14
     Congressman
    1.11
     Plaintiff
    1.10
     hereby
    1.07
     Defendants
    1.02
     Presidential
    0.99
     Senator
    0.96
     VERY
    0.95
     Plaint
    0.95
     Petition
    0.93
    Activations Density 1.048%

    No Known Activations