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. 23334
    Prev
    Next
    INDEX
    Explanations

    phrases related to growth or increase

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "expand" and its variations in different contexts

    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
    MET
    -0.77
    ndra
    -0.75
    ches
    -0.73
     ¯
    -0.73
    ICAN
    -0.69
    ched
    -0.69
    nee
    -0.69
    pas
    -0.68
    DER
    -0.68
    mir
    -0.68
    POSITIVE LOGITS
    ansion
    0.82
     expansion
    0.78
    onential
    0.75
    sheets
    0.73
     enormously
    0.73
     explos
    0.73
     outward
    0.72
    itals
    0.71
    utterstock
    0.69
     exponentially
    0.68
    Activations Density 0.026%

    No Known Activations