© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 20381
    Prev
    Next
    INDEX
    Explanations

    important actions or requirements in a set of instructions or guidelines

    oai_token-act-pair · gpt-3.5-turbo

    phrases or words indicating requirements or obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "}],"
    -0.59
    standing
    -0.55
     Confeder
    -0.55
    antics
    -0.55
    foreseen
    -0.54
    æĢ
    -0.54
    finding
    -0.53
    limits
    -0.53
    detail
    -0.52
    shall
    -0.52
    POSITIVE LOGITS
     Javascript
    0.67
     login
    0.66
    angan
    0.63
     reload
    0.61
     password
    0.60
    $$$$
    0.59
    tsy
    0.58
     JavaScript
    0.58
    afa
    0.57
     select
    0.57
    Activations Density 0.024%

    No Known Activations