© 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. 10797
    Prev
    Next
    INDEX
    Explanations

    mindset-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to strategies, deals, and agreements

    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
    Images
    -0.95
    inders
    -0.81
     Cosponsors
    -0.80
    ousands
    -0.78
    atars
    -0.77
    xes
    -0.75
    »Ĵ
    -0.74
    abytes
    -0.73
    姫
    -0.73
    features
    -0.73
    POSITIVE LOGITS
     thing
    1.37
     affair
    1.31
     situation
    1.13
     fest
    1.04
     issue
    1.04
     ploy
    1.04
    fest
    1.03
     joke
    1.00
     tactic
    1.00
     breaker
    0.97
    Activations Density 0.457%

    No Known Activations