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. 2041
    Prev
    Next
    INDEX
    Explanations

    references to physical elements such as pipes

    oai_token-act-pair · gpt-3.5-turbo

    references to pipes and their various contexts

    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
    enance
    -0.80
    ean
    -0.76
    orian
    -0.72
    nesota
    -0.71
     Maxwell
    -0.70
     Bei
    -0.70
    onia
    -0.70
    eanor
    -0.69
    ivals
    -0.68
     fixme
    -0.66
    POSITIVE LOGITS
    pipe
    1.09
     cleaners
    1.04
     pipe
    1.03
     pipes
    0.95
     piping
    0.86
     cleaner
    0.84
     condu
    0.82
     empt
    0.82
     Pipe
    0.82
     conduit
    0.80
    Activations Density 0.024%

    No Known Activations