© 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. 1-RES-JB
    11. 3929
    Prev
    Next
    INDEX
    Explanations

    specific details within a longer text, in this case, it activates for the word 'has'

    oai_token-act-pair · gpt-3.5-turbo

    the presence of Pokémon or gaming terminology related to actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esty
    -0.73
    Bank
    -0.66
    elsen
    -0.64
    wig
    -0.62
     Forms
    -0.61
    PASS
    -0.60
    ãĥŁ
    -0.60
    minist
    -0.60
     UNHCR
    -0.60
    ocide
    -0.60
    POSITIVE LOGITS
    ordering
    0.69
    '>
    0.68
    anza
    0.65
    pects
    0.64
    bral
    0.62
    lished
    0.62
    keyes
    0.61
    ourage
    0.59
    beard
    0.57
     Mellon
    0.57
    Activations Density 0.000%

    No Known Activations