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. 10-RES-JB
    6. 20981
    Prev
    Next
    INDEX
    Explanations

    adjectives related to a variety of different things

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "diverse" and related concepts of variety or eclecticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dur
    -0.78
    ultimate
    -0.73
    unia
    -0.72
    çͰ
    -0.72
    Roy
    -0.71
    Speed
    -0.68
    phies
    -0.66
    oldown
    -0.66
    /+
    -0.66
    Emb
    -0.64
    POSITIVE LOGITS
     perspectives
    1.10
     viewpoints
    1.09
     array
    0.99
     assortment
    0.99
     backgrounds
    0.98
    ively
    0.94
     assemb
    0.93
    iveness
    0.92
     spectrum
    0.90
     personalities
    0.87
    Activations Density 0.077%

    No Known Activations