© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3013
    Prev
    Next
    INDEX
    Explanations

    words related to increase or growth

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    concepts related to increases or growth in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    thing
    -0.86
    odore
    -0.74
    words
    -0.66
    oran
    -0.65
     reformed
    -0.63
    outhern
    -0.63
    inker
    -0.62
    facts
    -0.62
    prim
    -0.60
    DragonMagazine
    -0.59
    POSITIVE LOGITS
     likelihood
    1.13
     chances
    1.04
     throughput
    0.99
     productivity
    0.98
     efficiency
    0.96
     susceptibility
    0.96
     exponentially
    0.93
     visibility
    0.93
     entropy
    0.92
     yields
    0.90
    Activations Density 0.122%

    No Known Activations