INDEX

Explanations

place names and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RepeatedField

-0.67

rawDesc

-0.60

 CreateTagHelper

-0.55

twimg

-0.54

+#+#

-0.54

res

-0.54

APORE

-0.54

شاف

-0.53

 unknownFields

-0.52

rungsseite

-0.52

POSITIVE LOGITS

 imputation

0.54

Geplaatst

0.49

ėjimas

0.49

ậc

0.48

 Meksiku

0.48

 Вікіпе

0.48

 apothe

0.47

mentaux

0.47

mpi

0.47

basicConfig

0.47

Activations Density 0.368%

place names and locations

No Comments

No Known Activations