© 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. 3-RES-JB
    11. 15668
    Prev
    Next
    INDEX
    Explanations

    instances referring to or involving specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups referred to as "persons."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Accessory
    -0.75
    Phill
    -0.69
    âĺħâĺħ
    -0.69
    è¡
    -0.67
    Brexit
    -0.66
    ļéĨĴ
    -0.65
     recess
    -0.63
     Raiders
    -0.63
    enthal
    -0.63
    asio
    -0.62
    POSITIVE LOGITS
    hood
    0.93
    folk
    0.91
     who
    0.78
     persons
    0.78
    nel
    0.77
    soever
    0.74
    ngth
    0.73
     vaccinated
    0.73
     inhab
    0.72
     blinded
    0.71
    Activations Density 0.019%

    No Known Activations