© 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. 7-RES-JB
    6. 12616
    Prev
    Next
    INDEX
    Explanations

    dates or time-related events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "after" and related phrases indicating events or actions taken subsequently

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ardless
    -0.85
    ail
    -0.76
    odes
    -0.67
    olute
    -0.67
    ertain
    -0.66
    each
    -0.65
    atts
    -0.64
    isible
    -0.63
    etric
    -0.63
    ctive
    -0.63
    POSITIVE LOGITS
    actionDate
    0.86
     suspicions
    0.72
     Azerb
    0.69
     childhood
    0.65
     Johann
    0.65
     pledging
    0.63
     researching
    0.63
     initials
    0.63
    growth
    0.62
     necessity
    0.62
    Activations Density 0.406%

    No Known Activations