© 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. 6-RES-JB
    6. 15182
    Prev
    Next
    INDEX
    Explanations

    time stamps related to posted content

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Posted" followed by numerical timestamps indicating publication dates

    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
    isky
    -0.79
    ivo
    -0.77
    ishi
    -0.74
    fell
    -0.74
    fitting
    -0.72
    ingly
    -0.71
    ifted
    -0.70
    ugal
    -0.70
    atern
    -0.68
    ften
    -0.68
    POSITIVE LOGITS
    Posted
    0.70
    vertis
    0.68
    monton
    0.67
    MON
    0.66
    erick
    0.66
    itors
    0.65
    âĹ¼
    0.65
     Parade
    0.64
     siege
    0.63
     Thumbnails
    0.61
    Activations Density 0.015%

    No Known Activations