INDEX

Explanations

terms related to negligence or negative actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

الإنجليزية

-0.74

:]:

-0.72

رشف

-0.69

CodeAttribute

-0.67

harusnya

-0.67

AsUp

-0.65

 onAnimation

-0.64

ividual

-0.64

 '\\;'

-0.62

RetentionPolicy

-0.60

POSITIVE LOGITS

sizeCache

0.65

nek

0.61

 setuptools

0.55

 EXERC

0.54

 Вікіпе

0.53

 eggs

0.53

Lepid

0.52

NEG

0.52

Nek

0.52

exer

0.52

Activations Density 0.166%

terms related to negligence or negative actions

No Comments

No Known Activations