INDEX

Explanations

references to direction or orientation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

enumi

-0.66

readObject

-0.61

 MonoBehaviour

-0.60

onsored

-0.57

 handleMessage

-0.55

ofluor

-0.55

jadas

-0.52

CLS

-0.51

ofür

-0.51

ugar

-0.50

POSITIVE LOGITS

 unto

0.94

 Unto

0.86

 vnto

0.79

to

0.78

到

0.77

至

0.77

 προς

0.76

tothe

0.76

Personensuche

0.73

 nahilalakip

0.71

Activations Density 0.529%

references to direction or orientation

No Comments

No Known Activations