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. 3-RES-JB
    6. 10439
    Prev
    Next
    INDEX
    Explanations

    words related to physical locations or names containing "arsh"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Marsh" and variations related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     livest
    -0.71
     trickle
    -0.67
     careful
    -0.62
     behold
    -0.60
    phrine
    -0.60
     Jiu
    -0.58
     includ
    -0.58
    fam
    -0.58
    formance
    -0.58
     boycot
    -0.58
    POSITIVE LOGITS
    mallow
    1.36
    ield
    1.01
    adow
    1.00
    arsh
    0.91
    rawdownloadcloneembedreportprint
    0.90
    ãĥ¥
    0.89
    rapnel
    0.85
    abulary
    0.80
    auna
    0.79
    itans
    0.76
    Activations Density 0.007%

    No Known Activations