© 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. 3-RES-JB
    11. 20386
    Prev
    Next
    INDEX
    Explanations

    terms related to three-dimensional representation or depiction

    oai_token-act-pair · gpt-3.5-turbo

    references to different dimensions in a spatial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raltar
    -0.84
    KEN
    -0.80
    INST
    -0.74
    etts
    -0.73
    ãģĤ
    -0.71
    ãĤĮ
    -0.70
    recomm
    -0.66
    chance
    -0.66
    don
    -0.66
    said
    -0.65
    POSITIVE LOGITS
    imensional
    1.32
    dimensional
    0.86
     dimensional
    0.84
    ynamic
    0.75
    ependent
    0.73
    acet
    0.72
    dimension
    0.72
     representations
    0.71
     printers
    0.71
     distortions
    0.66
    Activations Density 0.010%

    No Known Activations