© 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. 2-RES-JB
    11. 21938
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations, particularly ones involving the term "Farm"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific farms or farming organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     funnel
    -0.85
     caster
    -0.80
     hypers
    -0.75
     limb
    -0.74
     revelation
    -0.73
     sender
    -0.73
     magician
    -0.73
     derail
    -0.73
     paddle
    -0.71
     implication
    -0.69
    POSITIVE LOGITS
    achev
    0.94
    ertodd
    0.94
    rolet
    0.82
    stead
    0.82
    adelphia
    0.81
    rats
    0.79
    rior
    0.79
     Pigs
    0.78
    erity
    0.78
    topia
    0.77
    Activations Density 0.025%

    No Known Activations