© 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. 6-RES-JB
    11. 11806
    Prev
    Next
    INDEX
    Explanations

    texts discussing the presence of specific information within something, such as containing elements, words, or materials

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "contain" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    doms
    -0.82
     Sabha
    -0.72
    urai
    -0.70
    yrim
    -0.66
    apo
    -0.63
     Seym
    -0.63
    laus
    -0.62
     Malk
    -0.61
    icably
    -0.61
    hon
    -0.60
    POSITIVE LOGITS
    ttes
    0.76
    ãĤ¼ãĤ¦ãĤ¹
    0.75
    encies
    0.75
     contents
    0.72
    nces
    0.70
    ãĤ£
    0.70
    ãĤ·ãĥ£
    0.69
    iveness
    0.68
    ãĤ©
    0.67
    ãĥĸ
    0.66
    Activations Density 0.034%

    No Known Activations