© 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. 4-RES-JB
    11. 12306
    Prev
    Next
    INDEX
    Explanations

    instances of lists of items or actions separated by commas

    oai_token-act-pair · gpt-3.5-turbo

    instances of commas

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

    No Comments

    Negative Logits
    ¬¼
    -0.78
    ishment
    -0.68
    itus
    -0.63
    ISION
    -0.61
    Į
    -0.60
    ONSORED
    -0.60
    emaker
    -0.59
    ary
    -0.57
    herent
    -0.57
    §
    -0.57
    POSITIVE LOGITS
     respectively
    1.18
     including
    1.09
     etc
    1.05
     albeit
    0.99
    Downloadha
    0.93
    including
    0.88
    etc
    0.87
     namely
    0.87
     Including
    0.83
     Flavoring
    0.82
    Activations Density 0.804%

    No Known Activations