© 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. 13903
    Prev
    Next
    INDEX
    Explanations

    land-related information, including agriculture, development, and conservation efforts

    oai_token-act-pair · gpt-3.5-turbo

    references to land use and agricultural practices

    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
     msec
    -0.83
    erity
    -0.82
    lycer
    -0.80
    ontent
    -0.75
    aughs
    -0.69
    bol
    -0.68
    76561
    -0.67
    illon
    -0.66
    ODY
    -0.66
    reads
    -0.65
    POSITIVE LOGITS
     inhabited
    1.25
     unpop
    1.22
     populated
    1.21
     barren
    1.19
     habitable
    1.14
     inaccessible
    1.14
     fertile
    1.13
     dotted
    1.11
     unexpl
    1.11
     littered
    1.11
    Activations Density 0.293%

    No Known Activations