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

    Neuronpedia

    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. 0-RES-JB
    11. 12036
    Prev
    Next
    INDEX
    Explanations

    the name "Martins" or similar variations

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Martin" or related terms

    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
    cffffcc
    -0.80
     pse
    -0.69
     curry
    -0.67
    jriwal
    -0.66
     opacity
    -0.65
     ESC
    -0.64
     subscribed
    -0.63
    pn
    -0.63
    518
    -0.63
    SR
    -0.63
    POSITIVE LOGITS
     Mart
    3.89
    Mart
    2.74
     mart
    2.20
    mart
    2.05
     Martinez
    1.47
     Marty
    1.28
     Martin
    1.25
     Martian
    1.12
     Maria
    1.06
     Bart
    1.06
    Activations Density 0.018%

    No Known Activations