© 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. 1-RES-JB
    11. 16811
    Prev
    Next
    INDEX
    Explanations

    phrases related to the action of bringing someone or something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "brought."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bi
    -0.66
    livious
    -0.65
    etheless
    -0.65
    rics
    -0.64
    dating
    -0.63
    onductor
    -0.63
     ellipt
    -0.62
    ede
    -0.62
    raid
    -0.61
    abet
    -0.60
    POSITIVE LOGITS
    bring
    0.86
     brought
    0.85
     forth
    0.76
    glers
    0.76
     ashore
    0.75
    xual
    0.74
     largeDownload
    0.73
    ĸļ
    0.72
     guests
    0.70
     bring
    0.68
    Activations Density 0.020%

    No Known Activations