© 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. 20164
    Prev
    Next
    INDEX
    Explanations

    references to mesh-related objects or concepts in computer graphics or simulations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "mesh" and its variations in the context of technical descriptions or explanations

    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
    =-=-=-=-
    -0.77
    ————————
    -0.76
    adobe
    -0.75
    ————
    -0.74
     Crus
    -0.69
    ership
    -0.68
    vernment
    -0.66
    humans
    -0.64
    perty
    -0.63
    decl
    -0.63
    POSITIVE LOGITS
     mesh
    1.10
     Mesh
    0.96
     meshes
    0.81
    Mesh
    0.72
    odox
    0.71
    lace
    0.70
    works
    0.66
    ugg
    0.66
     networking
    0.64
     fitting
    0.62
    Activations Density 0.007%

    No Known Activations