© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 2551
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons

    oai_token-act-pair · gpt-3.5-turbo

    the word "to" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     instit
    -0.63
     showers
    -0.62
     reperto
    -0.61
     refunds
    -0.60
     concentrated
    -0.58
     bidding
    -0.58
     evid
    -0.58
     heads
    -0.57
     congrat
    -0.56
     headed
    -0.56
    POSITIVE LOGITS
    ggles
    1.42
    wered
    1.28
    ilet
    1.09
    pless
    1.07
    othy
    1.03
    gg
    1.00
    asted
    0.99
    lling
    0.98
    adies
    0.98
    ppers
    0.97
    Activations Density 0.383%

    No Known Activations