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. 11-RES-JB
    6. 23590
    Prev
    Next
    INDEX
    Explanations

    phrases related to legacy or remembrance

    oai_token-act-pair · gpt-3.5-turbo

    references to legacy and remembrance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beforehand
    -0.82
    Minimum
    -0.73
    wk
    -0.70
    furt
    -0.70
     Setup
    -0.70
    intent
    -0.69
     coercion
    -0.67
     coord
    -0.67
    specified
    -0.66
    setup
    -0.66
    POSITIVE LOGITS
     memorial
    1.54
     remembrance
    1.49
     remem
    1.46
     descendants
    1.44
     commemor
    1.42
     nostalg
    1.42
     reminis
    1.36
     memories
    1.34
     nostalgia
    1.30
     historians
    1.30
    Activations Density 0.875%

    No Known Activations