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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-RES-JB
    6. 2846
    Prev
    Next
    INDEX
    Explanations

    words related to positive emotions and memories, particularly related to fondness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of fondness or nostalgia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irrel
    -0.75
    adesh
    -0.70
    ffen
    -0.70
    UGH
    -0.68
    UNCH
    -0.68
    atts
    -0.66
    udder
    -0.66
    abetic
    -0.65
    Tube
    -0.64
    KT
    -0.63
    POSITIVE LOGITS
     fond
    1.26
    entimes
    0.92
    ness
    0.89
    uously
    0.88
     farewell
    0.83
     memories
    0.83
     remem
    0.80
    nesses
    0.80
    uous
    0.74
    est
    0.73
    Activations Density 0.009%

    No Known Activations