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. 19040
    Prev
    Next
    INDEX
    Explanations

    mentions of groups of people or entities working together towards a common goal

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "and"

    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
    ukong
    -0.87
    lot
    -0.77
    igmatic
    -0.76
    PLE
    -0.70
    xt
    -0.69
    GMT
    -0.69
    ilk
    -0.69
    unction
    -0.69
    restling
    -0.68
    poral
    -0.68
    POSITIVE LOGITS
     pundits
    1.19
     commentators
    1.17
     journalists
    1.15
     analysts
    1.14
     stakeholders
    1.13
     collaborators
    1.10
     spectators
    1.09
     policymakers
    1.08
     bystanders
    1.07
     educators
    1.06
    Activations Density 0.192%

    No Known Activations