INDEX

Explanations

mentions of geographical locations and proper nouns

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

rån

-0.55

 houver

-0.52

 vulgaires

-0.51

ministerium

-0.51

щихся

-0.49

 تومان

-0.47

 obvious

-0.47

 étrangères

-0.46

utnik

-0.46

 suivantes

-0.46

POSITIVE LOGITS

tvguidetime

0.85

Efq

0.84

]='\

0.82

UnusedPrivate

0.80

########.

0.71

 utafitiHapana

0.70

 Monfieur

0.70

GEBURTS

0.68



0.68

 myſelf

0.66

Activations Density 0.331%

mentions of geographical locations and proper nouns

No Comments

No Known Activations