INDEX

Explanations

references to discrimination and inequity in various contexts

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

mentions of specific names, symbols, or technical elements, often related to programming, calculations, or data analysis.

oai_token-act-pair · gpt-4o Triggered by @timna

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 sécur

-0.48

 istrinya

-0.47

ießen

-0.45

 Everyone

-0.44

 grito

-0.44

 acompañ

-0.43

adpleegd

-0.43

 rağmen

-0.43

 kaca

-0.43

 ajuns

-0.42

POSITIVE LOGITS

 Roskov

0.81

Autoritní

0.72

 EconPapers

0.69

 tuong

0.60

ArgumentParser

0.59

SequentialGroup

0.58

 clearColor

0.57

^(@)

0.56

 kasarigan

0.55

occan

0.54

Activations Density 1.590%

references to discrimination and inequity in various contexts

mentions of specific names, symbols, or technical elements, often related to programming, calculations, or data analysis.

No Comments

No Known Activations