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. 21637
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Martinez"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Martinez."

    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
    umbn
    -1.00
    pir
    -0.91
    glers
    -0.80
    umption
    -0.79
    nel
    -0.75
    fare
    -0.75
    adder
    -0.75
    ĻĤ
    -0.74
    rencies
    -0.71
    ramid
    -0.71
    POSITIVE LOGITS
     Martinez
    1.26
    inez
    1.15
     Alonso
    0.81
     Chavez
    0.80
     Mons
    0.78
     Levy
    0.75
     Gomez
    0.73
     Ortiz
    0.73
     McCl
    0.72
     da
    0.71
    Activations Density 0.004%

    No Known Activations