© 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. 2870
    Prev
    Next
    INDEX
    Explanations

    keywords related to giving instructions or directing someone on what to do

    oai_token-act-pair · gpt-3.5-turbo

    imperative actions and suggestions for exploring or discussing topics

    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
    ago
    -0.73
    éĹ
    -0.70
    ELD
    -0.70
    bara
    -0.69
    lied
    -0.67
    à¨
    -0.66
    otten
    -0.64
    inished
    -0.63
    Downloadha
    -0.63
    owl
    -0.62
    POSITIVE LOGITS
     ourselves
    0.93
    querade
    0.75
     hypot
    0.64
    joice
    0.63
     Friendship
    0.63
     rg
    0.63
     clarify
    0.62
     illustrate
    0.59
     thee
    0.59
     REAL
    0.58
    Activations Density 0.061%

    No Known Activations