© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 975
    Prev
    Next
    INDEX
    Explanations

    mentions of people's last name "Martinez."

    oai_token-act-pair · gpt-3.5-turbo

    the name "Martinez" in various contexts and references

    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
    umbn
    -0.96
    glers
    -0.86
    pir
    -0.85
    umption
    -0.79
    fare
    -0.78
    tailed
    -0.77
    adder
    -0.76
    nel
    -0.75
    ĻĤ
    -0.73
    UTH
    -0.73
    POSITIVE LOGITS
     Martinez
    1.22
    inez
    1.18
     Mons
    0.84
    ards
    0.76
     Chavez
    0.76
    ynski
    0.75
     Alonso
    0.74
     Gomez
    0.74
     Ortiz
    0.74
     da
    0.73
    Activations Density 0.009%

    No Known Activations