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. 13044
    Prev
    Next
    INDEX
    Explanations

    the word "Ye" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the entity "Ye," indicating a focus on mentions of a specific person or character

    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
    ãĥ¼ãĥĨ
    -1.01
    Downloadha
    -0.81
    ITY
    -0.76
    ctica
    -0.75
    ãĥ´ãĤ¡
    -0.73
    ãĥ¼ãĥĨãĤ£
    -0.73
    lished
    -0.71
    ity
    -0.69
    ãĥĨ
    -0.68
    اÙĦ
    -0.68
    POSITIVE LOGITS
    ldon
    1.01
    ats
    0.92
    lda
    0.89
    oman
    0.88
    erk
    0.84
    aser
    0.81
    asing
    0.81
    igh
    0.80
    asers
    0.79
    hovah
    0.77
    Activations Density 0.012%

    No Known Activations