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

    Neuronpedia

    Jacobian LensNEW
    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. 20210
    Prev
    Next
    INDEX
    Explanations

    technical terms or code-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    hierarchical structures or rankings, particularly in the context of awards or gaming

    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
     telecom
    -0.63
     Venezuel
    -0.62
     bitcoin
    -0.61
     Bitcoin
    -0.59
     Airbnb
    -0.58
     Cheong
    -0.58
     Zika
    -0.58
     China
    -0.57
    Ukraine
    -0.57
     UAE
    -0.57
    POSITIVE LOGITS
     selecting
    0.62
     initiation
    0.61
     adjud
    0.60
     summ
    0.57
    Completed
    0.56
     concluding
    0.56
     staggered
    0.56
     assigned
    0.55
     admon
    0.55
     commenced
    0.55
    Activations Density 1.175%

    No Known Activations