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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 743
    Prev
    Next
    INDEX
    Explanations

    keywords related to nostalgia

    oai_token-act-pair · gpt-3.5-turbo

    themes of nostalgia and reminiscence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FT
    -0.68
    Princ
    -0.68
    Lind
    -0.68
    handle
    -0.66
    ŃĶ
    -0.65
    missions
    -0.64
    iop
    -0.63
    agram
    -0.63
    arent
    -0.62
    ARM
    -0.60
    POSITIVE LOGITS
     nostalg
    1.24
     nostalgia
    1.11
     nostalgic
    1.11
     memories
    1.07
     Memories
    0.98
    algia
    0.95
     reminis
    0.94
     fond
    0.86
     remembered
    0.85
     remem
    0.85
    Activations Density 0.013%

    No Known Activations