© 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. 1-RES-JB
    6. 6643
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "obs" or related variations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "obs."

    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
     Monarch
    -0.75
     slip
    -0.66
     Poles
    -0.66
    ãĥĥãĥī
    -0.66
     Serbia
    -0.64
    WAY
    -0.63
     Sakuya
    -0.63
     Italy
    -0.63
     ca
    -0.62
     historic
    -0.61
    POSITIVE LOGITS
    obs
    1.35
    ols
    1.06
    essed
    1.03
    poon
    1.01
    ushi
    0.99
    ugar
    0.97
    ilib
    0.97
    ullivan
    0.96
    essions
    0.96
    afety
    0.94
    Activations Density 0.005%

    No Known Activations