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. 3933
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a comparison between different aspects or options

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include alternatives or comparisons

    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
    successfully
    -0.78
    igned
    -0.68
    ially
    -0.64
    ETS
    -0.64
    umerous
    -0.63
    requently
    -0.62
    Duration
    -0.62
    egu
    -0.60
    ottesville
    -0.59
    erest
    -0.59
    POSITIVE LOGITS
    whatever
    1.74
     whatever
    1.73
     something
    1.42
    acle
    1.36
     anything
    1.28
     whoever
    1.27
     somet
    1.23
     whichever
    1.20
    chard
    1.20
     wherever
    1.13
    Activations Density 0.156%

    No Known Activations