INDEX

Explanations

active verbs and descriptive phrases related to personal achievements and qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

chach

-0.62

 Blech

-0.61

jíma

-0.55

seamnă

-0.54

 Kolo

-0.53

ismet

-0.53

ETHING

-0.52

ougou

-0.51

Unione

-0.51

tikum

-0.50

POSITIVE LOGITS

 himself

1.52

himself

1.20

 Himself

1.14

his

0.94

He

0.93

He

0.84

因为他

0.84

的他

0.81

His

0.81

he

0.80

Activations Density 0.321%

active verbs and descriptive phrases related to personal achievements and qualities

No Comments

No Known Activations