INDEX

Explanations

technical keywords related to data structure definitions and element types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

jfree

-0.61

GEBURTS

-0.57

égek

-0.55

 وتسجيلات

-0.53

 aérienne

-0.52

 jLabel

-0.51

bilidad

-0.50

waniu

-0.49

wiches

-0.49

ilever

-0.49

POSITIVE LOGITS

ted

1.26

ting

1.20

ts

1.01

ta

1.01

te

0.98

tes

0.97

to

0.95

ter

0.92

tos

0.91

tg

0.91

Activations Density 0.387%

technical keywords related to data structure definitions and element types

No Comments

No Known Activations