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. 3-RES-JB
    6. 10076
    Prev
    Next
    INDEX
    Explanations

    entities or terms related to software or computer programming such as 'navigator', 'executor', or 'dictator'

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to "ator" suffixes, primarily focusing on specific roles or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    earchers
    -0.77
    printed
    -0.76
    ĸļ
    -0.76
    lyak
    -0.73
    mbuds
    -0.67
     challeng
    -0.66
    vironment
    -0.66
     porous
    -0.65
    formed
    -0.63
     nep
    -0.63
    POSITIVE LOGITS
    ator
    0.91
    ators
    0.86
    oldemort
    0.81
    iola
    0.80
    ioch
    0.79
    ially
    0.77
    ios
    0.77
    berus
    0.76
    ibles
    0.73
    oad
    0.72
    Activations Density 0.019%

    No Known Activations