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. 1-RES-JB
    6. 17294
    Prev
    Next
    INDEX
    Explanations

    names with the prefix "Maj" in various contexts and settings

    oai_token-act-pair · gpt-3.5-turbo

    references to "Maj" or variations of it as a prominent figure or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PORT
    -0.71
    change
    -0.70
    flush
    -0.69
    VALUE
    -0.68
    clusive
    -0.67
     Jenner
    -0.66
    Interstitial
    -0.66
    porting
    -0.65
     damned
    -0.65
     Rainbow
    -0.64
    POSITIVE LOGITS
     Maj
    0.99
    undai
    0.98
    estic
    0.94
    ournal
    0.94
    adier
    0.83
     subsequ
    0.83
    unction
    0.81
    entary
    0.80
    unctions
    0.78
     veter
    0.78
    Activations Density 0.004%

    No Known Activations