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. 4-RES-JB
    6. 17825
    Prev
    Next
    INDEX
    Explanations

    verbs that imply action or involvement in certain activities

    oai_token-act-pair · gpt-3.5-turbo

    active verbs related to actions taken by organizations, individuals, or communities

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

    No Comments

    Negative Logits
    sac
    -0.66
     grouping
    -0.62
     Kinnikuman
    -0.60
     assumes
    -0.59
    zip
    -0.59
     Mes
    -0.57
    dt
    -0.57
    ijk
    -0.56
     ending
    -0.56
     preceding
    -0.56
    POSITIVE LOGITS
     Canaver
    0.77
    ADRA
    0.75
    Pixel
    0.69
    igated
    0.68
    urated
    0.68
    Edge
    0.68
    edge
    0.67
    hani
    0.67
    RAG
    0.67
    GGGGGGGG
    0.66
    Activations Density 0.364%

    No Known Activations