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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10818
    Prev
    Next
    INDEX
    Explanations

    Spanish names containing the letter 'ñ'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "ñ" in names or words

    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
    sonian
    -1.09
    ugu
    -0.86
    ovie
    -0.84
    nostic
    -0.82
    ologically
    -0.82
    estation
    -0.81
    raltar
    -0.81
    estones
    -0.79
    utenberg
    -0.79
    itarian
    -0.78
    POSITIVE LOGITS
     Nieto
    1.42
    ña
    1.17
     Herrera
    0.81
    ñ
    0.79
    ño
    0.78
     peppers
    0.77
     Calder
    0.75
     Cruz
    0.74
     MX
    0.71
    ÃŃa
    0.69
    Activations Density 0.013%

    No Known Activations