© 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. 3-RES-JB
    11. 6133
    Prev
    Next
    INDEX
    Explanations

    mentions of mysterious and significant objects or symbols

    oai_token-act-pair · gpt-3.5-turbo

    references to monolithic structures or concepts

    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
     welf
    -0.77
    parts
    -0.66
    Alternative
    -0.65
    shapeshifter
    -0.64
    Crime
    -0.64
     poss
    -0.64
    FUL
    -0.60
    models
    -0.60
     fel
    -0.59
    Altern
    -0.58
    POSITIVE LOGITS
    olith
    1.19
    otomy
    1.02
    olithic
    0.98
    uania
    0.94
    ography
    0.91
    ographic
    0.88
    eous
    0.86
    atically
    0.84
    ossus
    0.84
    ographically
    0.82
    Activations Density 0.027%

    No Known Activations