© 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. 10-RES-JB
    11. 18965
    Prev
    Next
    INDEX
    Explanations

    words related to the Earth or geological events

    oai_token-act-pair · gpt-3.5-turbo

    references to Earth and its characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bers
    -0.65
    ussen
    -0.63
     Sweeney
    -0.62
    acco
    -0.62
     trademarks
    -0.61
     Ernst
    -0.60
    osa
    -0.60
     convictions
    -0.59
     NF
    -0.58
     Gos
    -0.58
    POSITIVE LOGITS
    lings
    1.31
    worms
    1.25
    worm
    1.20
    sea
    1.02
    Bound
    1.00
     orbiting
    0.99
     orbit
    0.98
    shine
    0.98
    arium
    0.95
    works
    0.94
    Activations Density 0.026%

    No Known Activations