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. 9-RES-JB
    6. 21276
    Prev
    Next
    INDEX
    Explanations

    numerical data results and analyses

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to research findings and results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iage
    -0.76
    lication
    -0.74
    emis
    -0.71
    choice
    -0.69
    ski
    -0.65
    chens
    -0.65
    anism
    -0.65
     Quit
    -0.64
    roying
    -0.62
     unsuccessfully
    -0.61
    POSITIVE LOGITS
     conclusive
    0.96
     damning
    0.88
     unequiv
    0.87
     skewed
    0.87
     alarming
    0.86
     preliminary
    0.85
     summarized
    0.84
     incon
    0.83
     disappointing
    0.83
     trickle
    0.82
    Activations Density 0.290%

    No Known Activations