© 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. 793
    Prev
    Next
    INDEX
    Explanations

    specific references to Office 365

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "365."

    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
    ngth
    -0.85
    hran
    -0.75
    geon
    -0.73
    iger
    -0.72
    oxin
    -0.70
    aped
    -0.70
    placed
    -0.68
    ocard
    -0.66
     fault
    -0.66
    andal
    -0.65
    POSITIVE LOGITS
     ILCS
    1.08
     365
    0.95
    365
    0.93
    ertodd
    0.80
    cffff
    0.78
    iations
    0.78
    iencies
    0.75
    20439
    0.72
    INESS
    0.72
    ternity
    0.71
    Activations Density 0.022%

    No Known Activations