© 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. 0-RES-JB
    11. 8154
    Prev
    Next
    INDEX
    Explanations

    words related to atmospheric layers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to different spheres or layers of the Earth and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     accountant
    -0.65
     Alban
    -0.63
     che
    -0.62
    tti
    -0.62
     officers
    -0.62
     dealer
    -0.61
     Form
    -0.61
     defective
    -0.59
     0004
    -0.58
     accounting
    -0.58
    POSITIVE LOGITS
    osphere
    4.58
    osp
    1.04
    mosp
    1.02
    isphere
    1.00
    liest
    1.00
    sonian
    0.96
     Nebula
    0.94
    ularity
    0.92
     Gaia
    0.89
    storms
    0.88
    Activations Density 0.015%

    No Known Activations