© 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. 7-RES-JB
    11. 4360
    Prev
    Next
    INDEX
    Explanations

    dates and other information related to events or documents

    oai_token-act-pair · gpt-3.5-turbo

    metadata elements, particularly details about authors, dates, and descriptive tags

    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
     forgetting
    -0.70
    raq
    -0.66
     rede
    -0.65
     disg
    -0.64
     coughing
    -0.63
     Haram
    -0.63
     flee
    -0.62
    ysis
    -0.61
     shred
    -0.60
     forget
    -0.60
    POSITIVE LOGITS
    isine
    0.92
    escription
    0.90
    Status
    0.89
    Narr
    0.88
    ometown
    0.86
    Duration
    0.84
    podcast
    0.84
    price
    0.83
    Age
    0.82
    Date
    0.81
    Activations Density 0.250%

    No Known Activations