© 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. 20495
    Prev
    Next
    INDEX
    Explanations

    words ending in "se" or "pse" combined with a numerical activation, indicating a specific pattern or code within a text

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "seem," indicating an exploration of perception or subjective experience

    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
     Banner
    -0.77
     overhead
    -0.63
    lessly
    -0.62
     realism
    -0.61
     barr
    -0.60
     BT
    -0.60
     pins
    -0.59
     Lovecraft
    -0.59
     Mellon
    -0.58
     securely
    -0.58
    POSITIVE LOGITS
    gments
    1.43
    venth
    1.42
    ems
    1.35
    ldom
    1.34
    gment
    1.34
    asons
    1.33
    eker
    1.32
    eming
    1.30
    gregation
    1.28
    aled
    1.26
    Activations Density 0.029%

    No Known Activations