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. 3075
    Prev
    Next
    INDEX
    Explanations

    the surname "Mul" with varying numbers following it

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Mul

    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
    xx
    -0.69
    ord
    -0.68
     arbitration
    -0.64
     robotics
    -0.64
     quake
    -0.63
    cold
    -0.63
     bent
    -0.61
    EEE
    -0.59
    Client
    -0.59
    eva
    -0.59
    POSITIVE LOGITS
     Mul
    4.04
     mul
    1.78
     Mush
    1.30
     Mn
    1.26
     Cull
    1.17
     Poc
    1.16
     Mulcair
    1.13
     Cul
    1.07
     Mull
    1.06
     Pul
    1.06
    Activations Density 0.014%

    No Known Activations