© 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. 11-RES-JB
    11. 14446
    Prev
    Next
    INDEX
    Explanations

    phrases related to human impact on the environment

    oai_token-act-pair · gpt-3.5-turbo

    references to human impact on the environment

    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
    é¾įå
    -0.72
    chell
    -0.69
    liga
    -0.67
    bg
    -0.66
    maxwell
    -0.63
    forth
    -0.63
    roller
    -0.63
     Seym
    -0.62
     Mechdragon
    -0.62
    href
    -0.62
    POSITIVE LOGITS
    oids
    1.31
     beings
    1.29
    zee
    1.01
    oid
    0.98
     readable
    0.88
     embryonic
    0.85
     physiology
    0.81
     genome
    0.80
    itarian
    0.79
    zees
    0.79
    Activations Density 0.031%

    No Known Activations