© 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. 9-RES-JB
    11. 18402
    Prev
    Next
    INDEX
    Explanations

    references to locations or destinations

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and conjunctions indicating narrative progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     microbiome
    -0.86
    pport
    -0.81
     enriched
    -0.77
     associations
    -0.75
     quir
    -0.73
     curated
    -0.73
     benchmark
    -0.73
     fielded
    -0.72
    riv
    -0.72
    adian
    -0.71
    POSITIVE LOGITS
     Afterwards
    1.83
     Shortly
    1.64
     Later
    1.63
     Eventually
    1.62
     However
    1.53
     Meanwhile
    1.53
     Soon
    1.49
     Immediately
    1.47
     Whilst
    1.46
     Upon
    1.44
    Activations Density 0.290%

    No Known Activations