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. 17655
    Prev
    Next
    INDEX
    Explanations

    words related to exceptional examples or extreme cases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to symbolic representation and embodiment of concepts

    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
    foreseen
    -0.96
    jab
    -0.82
    ften
    -0.66
    swer
    -0.65
    peer
    -0.63
    supp
    -0.61
    leased
    -0.60
    picking
    -0.60
    asive
    -0.60
    heed
    -0.60
    POSITIVE LOGITS
    imum
    0.92
     embodiment
    0.84
     virtues
    0.81
     qualities
    0.80
     exempl
    0.76
     archetype
    0.75
     perfection
    0.74
     ideal
    0.73
     example
    0.73
     excellence
    0.73
    Activations Density 0.187%

    No Known Activations