© 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 EvalsExportsinterp-engineNEWAPI 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. 1-RES-JB
    11. 9566
    Prev
    Next
    INDEX
    Explanations

    references to a person named Roberto

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Roberto."

    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
     CPC
    -0.84
    ä¹ĭ
    -0.80
    scl
    -0.79
    ym
    -0.75
    áµ
    -0.70
    edy
    -0.70
    sg
    -0.68
     Citizens
    -0.67
    holders
    -0.67
    ////////
    -0.65
    POSITIVE LOGITS
     Roberto
    1.22
     Ezek
    0.86
     Martinez
    0.85
    angelo
    0.85
     Carlos
    0.83
     Pablo
    0.82
     Clement
    0.81
    Rober
    0.81
     Rican
    0.80
    ardo
    0.80
    Activations Density 0.005%

    No Known Activations