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. 3841
    Prev
    Next
    INDEX
    Explanations

    proper nouns starting with 'Marqu'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or entities, particularly "Marqu" and "Xavier"

    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
     Survivors
    -0.82
    fulness
    -0.74
     CBI
    -0.70
    light
    -0.67
     Cf
    -0.66
     Antar
    -0.65
     Kali
    -0.63
     DEFENSE
    -0.61
     Racial
    -0.61
     Hera
    -0.60
    POSITIVE LOGITS
    ette
    1.11
    ois
    0.95
    ajo
    0.95
    erey
    0.93
    naire
    0.90
     Marqu
    0.89
    essor
    0.88
    alties
    0.88
    esses
    0.87
    ettes
    0.87
    Activations Density 0.008%

    No Known Activations