© 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. 1-RES-JB
    11. 24260
    Prev
    Next
    INDEX
    Explanations

    the word "Caballo"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual, likely linked to sports or entertainment

    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
    DonaldTrump
    -0.78
    Downloadha
    -0.75
    ãĥĦ
    -0.73
    FTWARE
    -0.73
    hirt
    -0.69
    66666666
    -0.68
     VICE
    -0.66
    iband
    -0.65
    åħī
    -0.63
    ENGTH
    -0.63
    POSITIVE LOGITS
     Cab
    1.18
    aret
    1.03
    ulic
    1.00
    abal
    0.89
     cab
    0.84
    oline
    0.81
     marqu
    0.75
    uana
    0.74
    itol
    0.72
    ez
    0.72
    Activations Density 0.003%

    No Known Activations