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. 2-RES-JB
    6. 13242
    Prev
    Next
    INDEX
    Explanations

    terms related to events or actions that follow or result from something else

    oai_token-act-pair · gpt-3.5-turbo

    the word "subsequent" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Haram
    -0.85
    rod
    -0.79
    tics
    -0.77
    eye
    -0.76
    Bay
    -0.75
    lua
    -0.75
    toe
    -0.69
    mberg
    -0.69
    park
    -0.69
    eping
    -0.69
    POSITIVE LOGITS
     generations
    1.04
     iterations
    1.00
     installments
    0.97
    wcs
    0.89
     batches
    0.89
     unsuccessful
    0.86
    ĸļ
    0.85
     editions
    0.85
     revisions
    0.84
     subsequent
    0.83
    Activations Density 0.004%

    No Known Activations