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. 21646
    Prev
    Next
    INDEX
    Explanations

    phrases related to organized groups and committees

    oai_token-act-pair · gpt-3.5-turbo

    references to organized groups or teams and their activities

    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
     Fountain
    -0.65
     breeze
    -0.62
     cents
    -0.62
     souven
    -0.61
    jar
    -0.61
    washer
    -0.59
     Paraly
    -0.59
     lows
    -0.59
     impairment
    -0.58
     blasphemy
    -0.58
    POSITIVE LOGITS
     comprised
    1.30
    members
    1.28
     disbanded
    1.28
     convened
    1.23
     consisting
    1.23
     chaired
    1.22
    Members
    1.20
     composed
    1.16
     formed
    1.11
     assembled
    1.09
    Activations Density 0.570%

    No Known Activations