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. 0-RES-JB
    6. 23891
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rain."

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the substring 'ra'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wang
    -0.78
    creen
    -0.74
     Siem
    -0.74
     Phillip
    -0.71
     LG
    -0.71
     Younger
    -0.69
     Ful
    -0.69
    employment
    -0.68
    elect
    -0.67
    pair
    -0.66
    POSITIVE LOGITS
     ra
    3.71
     Raider
    2.04
    Ra
    1.66
     gra
    1.19
    ra
    1.19
    rax
    1.06
     RA
    1.06
     raiding
    0.98
    RA
    0.95
    raising
    0.90
    Activations Density 0.025%

    No Known Activations