INDEX

Explanations

references to academic roles and positions within educational institutions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Wiktionnaire

-0.56

CLUDING

-0.51

 елның

-0.51

Distribuzione

-0.51

archiviato

-0.50

 tolerance

-0.50

CAPTION

-0.48

 IEnumerator

-0.48

broek

-0.48

字

-0.47

POSITIVE LOGITS

 teaching

0.83

 teach

0.81

 faculty

0.75

 mengajar

0.75

teaching

0.72

 lecturing

0.72

 teaches

0.69

 docente

0.68

 Teaching

0.68

Teaching

0.67

Activations Density 0.148%

references to academic roles and positions within educational institutions

No Comments

No Known Activations