© 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 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. 4-RES-JB
    11. 2082
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of matter

    oai_token-act-pair · gpt-3.5-turbo

    references to matter in various contexts related to physics and the universe

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

    No Comments

    Negative Logits
    olkien
    -0.77
    udeb
    -0.75
     corrid
    -0.72
    ESCO
    -0.71
    CHR
    -0.69
     Palestin
    -0.69
    inka
    -0.64
    gency
    -0.64
    adier
    -0.64
    ãĥ³ãĤ¸
    -0.64
    POSITIVE LOGITS
    matter
    0.93
    flows
    0.89
    ername
    0.85
    pace
    0.83
     particles
    0.82
     Matter
    0.79
    bender
    0.77
    flow
    0.77
     ions
    0.77
    bending
    0.76
    Activations Density 0.018%

    No Known Activations