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. 8-RES-JB
    6. 4684
    Prev
    Next
    INDEX
    Explanations

    verbs related to blurring or blending

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of blending or merging boundaries

    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
    ept
    -0.73
    phis
    -0.67
    pta
    -0.66
    iott
    -0.65
    penter
    -0.64
    krit
    -0.63
    anto
    -0.62
    alg
    -0.62
    sat
    -0.62
    eering
    -0.61
    POSITIVE LOGITS
    ected
    0.80
    lights
    0.79
     blend
    0.73
     blending
    0.71
    toggle
    0.70
    rily
    0.68
     colors
    0.64
    orph
    0.64
    COLOR
    0.63
     recol
    0.63
    Activations Density 0.082%

    No Known Activations