© 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. 7-RES-JB
    11. 1547
    Prev
    Next
    INDEX
    Explanations

    sentences containing a period

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases that indicate actions and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ordinary
    -0.85
     policymakers
    -0.77
     displacement
    -0.77
     diseng
    -0.76
     suppressed
    -0.74
     patrol
    -0.74
     employment
    -0.74
    ordinary
    -0.73
     depreciation
    -0.72
     temperament
    -0.72
    POSITIVE LOGITS
     Anyway
    1.35
     Needless
    1.32
     Seriously
    1.21
     Seems
    1.20
     Basically
    1.20
     Oops
    1.19
     Funny
    1.18
     Hopefully
    1.18
     Featuring
    1.17
     Apparently
    1.17
    Activations Density 0.599%

    No Known Activations