© 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. 8-RES-JB
    11. 8843
    Prev
    Next
    INDEX
    Explanations

    words related to official declarations or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "officially" and similar terms, indicating formal declarations or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.87
     Emin
    -0.73
    nesota
    -0.70
    rug
    -0.69
    ngth
    -0.67
    oute
    -0.66
    wich
    -0.65
    vich
    -0.65
    ieri
    -0.64
     Recession
    -0.64
    POSITIVE LOGITS
     sanctioned
    1.04
     announced
    0.90
     disbanded
    0.88
     endorsed
    0.86
     declared
    0.86
     acknowledged
    0.84
     ratified
    0.84
    announced
    0.83
     apologized
    0.83
     christ
    0.83
    Activations Density 0.034%

    No Known Activations