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. 6998
    Prev
    Next
    INDEX
    Explanations

    personal names predominantly starting with the letters "Tim"

    oai_token-act-pair · gpt-3.5-turbo

    proper names and significant individuals related to a specific context

    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
    Ô
    -0.93
    å¦
    -0.72
    æĢ
    -0.71
     Proposition
    -0.70
    MAT
    -0.68
    FACE
    -0.68
     largeDownload
    -0.68
    è£
    -0.65
    ModLoader
    -0.64
    HER
    -0.64
    POSITIVE LOGITS
    umatic
    0.97
    rican
    0.75
    icky
    0.73
    opol
    0.68
    osaurus
    0.67
    henko
    0.65
    zik
    0.64
    ndra
    0.64
    ockets
    0.64
    opolis
    0.64
    Activations Density 0.116%

    No Known Activations