INDEX

Explanations

geographical locations and significant events associated with them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

latable

-0.56

act

-0.55

 return

-0.54

 practice

-0.54

 fast

-0.52

 sign

-0.52

sit

-0.51

élie

-0.51

 limit

-0.50

 typelib

-0.49

POSITIVE LOGITS

 CURIAM

0.71

 صوتيه

0.70

 defaultstate

0.69

Tembelea

0.66

 kasarigan

0.63

 gynhyrchwyd

0.61

+#+#

0.60

 Vaticano

0.60

IntoConstraints

0.59

UnitTesting

0.59

Activations Density 0.329%

geographical locations and significant events associated with them

No Comments

No Known Activations