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. 1-RES-JB
    6. 19191
    Prev
    Next
    INDEX
    Explanations

    geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations, especially in the context of lyrics and cultural activities involving children and nature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    culosis
    -0.77
     Jindal
    -0.70
     Baird
    -0.70
    FILE
    -0.69
     Mayer
    -0.67
     McAuliffe
    -0.65
    ²¾
    -0.64
     Goldberg
    -0.63
     Germ
    -0.62
     Mitt
    -0.62
    POSITIVE LOGITS
    seys
    1.25
    ynt
    0.89
    ynthesis
    0.89
    peak
    0.88
    arbon
    0.85
     Aires
    0.85
    hips
    0.83
    eeds
    0.79
    ilk
    0.77
    imilar
    0.77
    Activations Density 0.030%

    No Known Activations