Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 20392
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to official announcements or declarations

    oai_token-act-pair · gpt-3.5-turbo

    the word "officially" and its variations indicating formality or confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.93
    wich
    -0.76
     Emin
    -0.72
     Mong
    -0.69
    lihood
    -0.68
    ritch
    -0.67
     Prospect
    -0.65
    ocene
    -0.65
    vich
    -0.65
    rug
    -0.64
    POSITIVE LOGITS
     sanctioned
    0.89
    dom
    0.86
    named
    0.84
     cleared
    0.84
     disbanded
    0.82
     declass
    0.78
     declared
    0.76
     recognised
    0.76
    ordered
    0.74
     recognized
    0.74
    Activations Density 0.017%

    No Known Activations