INDEX

Explanations

numerical data or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

saraba

-0.61

AutoField

-0.59

تقاوى

-0.56

con

-0.55

Havolalar

-0.54

kháu

-0.53

quial

-0.53

sizeCache

-0.51

/${

-0.50

POSITIVE LOGITS

 CURIAM

0.91

 stepmother

0.72

 مشين

0.71

BeforeMethod

0.66

writeFieldEnd

0.66

 Thirdly

0.63

PhysRevD

0.61

UnusedPrivate

0.61

 Trabal

0.60

Captor

0.60

Activations Density 0.160%

numerical data or statistics

No Comments

No Known Activations