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. 5-RES-JB
    6. 5013
    Prev
    Next
    INDEX
    Explanations

    objects or concepts related to rubber

    oai_token-act-pair · gpt-3.5-turbo

    references to rubber

    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
    ulhu
    -0.88
    arios
    -0.84
    erest
    -0.84
    emi
    -0.83
    orld
    -0.80
    rophe
    -0.76
    ################
    -0.74
    iry
    -0.72
    soType
    -0.70
    achusetts
    -0.70
    POSITIVE LOGITS
     latex
    0.94
     ding
    0.93
    neck
    0.93
     rubber
    0.91
     duck
    0.84
     Rubber
    0.82
     tubing
    0.81
    maid
    0.81
     band
    0.80
     glove
    0.79
    Activations Density 0.013%

    No Known Activations