INDEX

Explanations

references to errors or failures related to image processing or handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Holstein

-0.51

 silicona

-0.50

 plomo

-0.49

-0.46

 Sarmiento

-0.44

DriverManager

-0.43

Geografie

-0.43

Si

-0.42

 familiale

-0.42

POSITIVE LOGITS

OGND

0.78

 referenties

0.72

mybatisplus

0.64

 мәкал

0.64

MENAFN

0.62

ftagPool

0.61

 noDo

0.61

 nakalista

0.60

دانشنامهٔ

0.59

Efq

0.57

Activations Density 0.113%

references to errors or failures related to image processing or handling

No Comments

No Known Activations