© 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. 11-RES-JB
    11. 17325
    Prev
    Next
    INDEX
    Explanations

    technical or financial terms and details

    oai_token-act-pair · gpt-3.5-turbo

    terms related to changes, updates, and significant details in the context of events or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    was
    -0.76
     hopes
    -0.75
     regrets
    -0.65
    Recipe
    -0.63
    Recomm
    -0.62
     Needs
    -0.62
    76561
    -0.61
     HAS
    -0.61
     owes
    -0.59
     loves
    -0.58
    POSITIVE LOGITS
     arise
    1.46
     collide
    1.34
     are
    1.33
     occur
    1.32
     emerge
    1.32
     arrive
    1.25
     converge
    1.23
     expire
    1.22
     begin
    1.21
     coincide
    1.20
    Activations Density 0.226%

    No Known Activations