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. 1519
    Prev
    Next
    INDEX
    Explanations

    adverbs describing the speed or manner in which something is done

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditions or circumstances that allow actions to occur

    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
    ebus
    -0.63
    cock
    -0.61
    orio
    -0.61
    SPONSORED
    -0.60
    ierre
    -0.59
    ahime
    -0.58
    ored
    -0.56
    ibles
    -0.56
    ivas
    -0.55
    ariat
    -0.55
    POSITIVE LOGITS
     independently
    0.86
    through
    0.85
    aneously
    0.82
    within
    0.80
     spor
    0.80
     by
    0.79
    BuyableInstoreAndOnline
    0.77
     anonymously
    0.77
     differently
    0.76
    ãĤ´ãĥ³
    0.75
    Activations Density 0.226%

    No Known Activations