© 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. 1-RES-JB
    11. 14553
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "matter" with different variations

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "matter."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORK
    -0.78
    LV
    -0.75
    ork
    -0.66
    CVE
    -0.66
    orks
    -0.64
    KEY
    -0.63
    KN
    -0.62
    Gaza
    -0.62
     HELP
    -0.61
    GMT
    -0.61
    POSITIVE LOGITS
    atter
    1.04
    bats
    0.89
    geist
    0.87
    deen
    0.85
    aton
    0.84
    oton
    0.81
    iever
    0.81
    icator
    0.78
    rower
    0.77
    jee
    0.77
    Activations Density 0.007%

    No Known Activations