© 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. 6-RES-JB
    11. 11870
    Prev
    Next
    INDEX
    Explanations

    proper nouns or named entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "identified" in various contexts

    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
    issance
    -0.78
    ights
    -0.75
     enjoyment
    -0.73
    imeo
    -0.71
    eries
    -0.69
    stead
    -0.67
    iths
    -0.67
    idth
    -0.66
    ework
    -0.64
    grain
    -0.64
    POSITIVE LOGITS
     Cosponsors
    0.87
     surn
    0.82
     alias
    0.77
     redacted
    0.77
     Forensic
    0.77
     deceased
    0.75
     names
    0.72
    onyms
    0.72
    rified
    0.71
     Identified
    0.70
    Activations Density 0.078%

    No Known Activations