© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-JB
    11. 10496
    Prev
    Next
    INDEX
    Explanations

    dimensions of images expressed as pixels

    oai_token-act-pair · gpt-3.5-turbo

    specific numeric values related to measurements or dimensions

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

    No Comments

    Negative Logits
    actic
    -0.86
    kson
    -0.85
    uana
    -0.85
    bone
    -0.82
    puter
    -0.82
    doms
    -0.81
    tails
    -0.79
    ptive
    -0.78
    pora
    -0.76
    axy
    -0.74
    POSITIVE LOGITS
    éĹĺ
    0.90
    ells
    0.72
     Seym
    0.71
    ickers
    0.71
     Lans
    0.67
     fullest
    0.67
     Sheen
    0.66
     Parables
    0.65
    ucket
    0.64
    384
    0.63
    Activations Density 0.029%

    No Known Activations