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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 4250
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically first names like "Ivan" and "Igor."

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly those starting with "Ivan" or "Igor."

    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
    Score
    -0.74
    aver
    -0.69
    reads
    -0.68
    inals
    -0.67
    Scient
    -0.65
    Gameplay
    -0.65
    ĻĤ
    -0.64
    Americans
    -0.63
    woman
    -0.63
    Methods
    -0.62
    POSITIVE LOGITS
    ovich
    1.15
     Ivan
    1.06
    hoe
    1.01
    ovic
    0.93
    opol
    0.92
    ova
    0.77
    imov
    0.76
    stadt
    0.76
     Ily
    0.75
    Äį
    0.75
    Activations Density 0.012%

    No Known Activations