© 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. 8-RES-JB
    11. 7778
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the comparison or similarity between different situations or elements

    oai_token-act-pair · gpt-3.5-turbo

    instances of comparative phrases indicating similarity or correlation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rumble
    -0.74
    ocene
    -0.69
     bang
    -0.64
     Stockholm
    -0.60
     Dota
    -0.59
    GET
    -0.58
     kindly
    -0.57
     Ventura
    -0.54
     Cause
    -0.54
     genuinely
    -0.54
    POSITIVE LOGITS
    forward
    0.81
     situated
    0.75
    withstanding
    0.74
     inclined
    0.74
    quartered
    0.73
    blance
    0.73
     minded
    0.71
    etheless
    0.70
    apy
    0.70
    forth
    0.69
    Activations Density 0.027%

    No Known Activations