© 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. 18925
    Prev
    Next
    INDEX
    Explanations

    proper nouns representing individuals and their associated actions or attributes

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals

    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
     highs
    -0.70
    ģ«
    -0.67
     PEOPLE
    -0.67
     fog
    -0.64
     tune
    -0.64
     TBA
    -0.64
     shitty
    -0.62
     Defin
    -0.62
     unfavorable
    -0.62
    Spoiler
    -0.61
    POSITIVE LOGITS
    iewicz
    0.86
    oyer
    0.78
    aird
    0.77
    uala
    0.77
    geon
    0.76
    rity
    0.76
    hari
    0.76
    iman
    0.75
    tsky
    0.75
    yip
    0.75
    Activations Density 0.167%

    No Known Activations