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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 8-RES-JB
    6. 5391
    Prev
    Next
    INDEX
    Explanations

    words related to objects or actions involving rubber

    oai_token-act-pair · gpt-3.5-turbo

    references to rubber and its various applications or connotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erest
    -0.84
    emi
    -0.81
    orld
    -0.80
    arios
    -0.76
    rophe
    -0.75
    ulhu
    -0.73
    places
    -0.73
    erers
    -0.72
    erer
    -0.72
    erent
    -0.71
    POSITIVE LOGITS
    ized
    0.97
     latex
    0.97
    neck
    0.95
     tubing
    0.88
     bands
    0.87
    band
    0.86
     rubber
    0.85
     gloves
    0.84
     ding
    0.82
     band
    0.82
    Activations Density 0.016%

    No Known Activations