INDEX

Explanations

references to the act of eating or food-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

UpInside

-0.77

stdc

-0.71

CppCodeGen

-0.69

发表于

-0.69

ύτε

-0.67

awtextra

-0.66

########.

-0.64

libft

-0.63

QMetaType

-0.63

Omg

-0.63

POSITIVE LOGITS

 indeed

0.70

Lot

0.61

 certainly

0.59

lot

0.59

Lot

0.58

 heavy

0.57

 hefty

0.56

 plenty

0.56

heavy

0.54

certainly

0.54

Activations Density 0.297%

references to the act of eating or food-related concepts

No Comments

No Known Activations