© 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. 2638
    Prev
    Next
    INDEX
    Explanations

    number values associated with measurements of area or quantity

    oai_token-act-pair · gpt-3.5-turbo

    measurements of area and cooking ingredients

    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
    mand
    -0.74
     bearer
    -0.71
    plex
    -0.69
     Turing
    -0.68
     Halls
    -0.68
    tumblr
    -0.65
    phrine
    -0.65
    hook
    -0.64
    ForgeModLoader
    -0.63
    proof
    -0.61
    POSITIVE LOGITS
    .,
    1.08
    ./
    0.90
    .;
    0.87
     seq
    0.86
    icka
    0.86
    hered
    0.86
    vl
    0.85
    .?
    0.81
    ubs
    0.78
    iece
    0.77
    Activations Density 0.024%

    No Known Activations