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. 6-RES-JB
    6. 23656
    Prev
    Next
    INDEX
    Explanations

    phrases related to things being spread out or distributed

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of scattering or dispersing objects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sen
    -0.79
    acl
    -0.75
    ocker
    -0.63
    Fight
    -0.63
     escalate
    -0.61
    POST
    -0.61
    iasis
    -0.61
    ibur
    -0.61
    uana
    -0.60
    resses
    -0.60
    POSITIVE LOGITS
     scattered
    1.00
    mble
    0.89
    sheets
    0.86
     scatter
    0.81
     scattering
    0.78
     dispersed
    0.77
    achusetts
    0.75
     bom
    0.75
     dispers
    0.75
    ت
    0.74
    Activations Density 0.037%

    No Known Activations