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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21836
    Prev
    Next
    INDEX
    Explanations

    phrases related to offering a variety of options or choices

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases indicating abundance or variety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    witz
    -0.65
    onen
    -0.65
     WARN
    -0.60
     Unch
    -0.59
    ortium
    -0.56
     Quart
    -0.56
    WARE
    -0.53
    OIL
    -0.52
    ortmund
    -0.52
    panel
    -0.51
    POSITIVE LOGITS
     alike
    0.74
    cellaneous
    0.73
     respectively
    0.64
     assorted
    0.64
     etc
    0.63
     thereof
    0.62
    estyles
    0.61
    whatever
    0.61
    endars
    0.60
     importantly
    0.60
    Activations Density 0.544%

    No Known Activations