© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 9966
    Prev
    Next
    INDEX
    Explanations

    references to different organizations or groups named "People"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "People," particularly in relation to organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lank
    -0.75
    forth
    -0.72
    Operation
    -0.68
     srfAttach
    -0.68
    CCC
    -0.63
    iffe
    -0.63
     Hick
    -0.62
    DERR
    -0.61
     Sadd
    -0.60
     Cain
    -0.60
    POSITIVE LOGITS
    hood
    0.91
    Unknown
    0.88
     Eater
    0.81
    uscript
    0.80
    folk
    0.80
    auri
    0.78
    hate
    0.77
    chu
    0.74
    aganda
    0.73
     smugglers
    0.72
    Activations Density 0.067%

    No Known Activations