© 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. 8-RES-JB
    11. 2535
    Prev
    Next
    INDEX
    Explanations

    references to specific items, such as articles, memos, or events

    oai_token-act-pair · gpt-3.5-turbo

    references to articles and organized discussions related to societal issues and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mayo
    -0.58
     Dane
    -0.58
    DAQ
    -0.57
    Category
    -0.56
     Oval
    -0.56
     Pru
    -0.55
    ãĥĥãĥī
    -0.55
    Ire
    -0.54
    bledon
    -0.54
    RELATED
    -0.53
    POSITIVE LOGITS
    ↵Âł
    0.90
     ·
    0.84
     ][
    0.83
     Âł
    0.81
     ..........
    0.77
    ³³³
    0.73
     ]
    0.72
     ....
    0.70
     ³³
    0.70
    îĢ
    0.68
    Activations Density 0.920%

    No Known Activations