INDEX

Explanations

details related to dialogue and character interactions

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

 whoſe

-0.71

 ſhould

-0.68

 myſelf

-0.66

 juſt

-0.66

 juſ

-0.63

 uſed

-0.63

 ſtate

-0.61

 ſtand

-0.60

 beſt

-0.60

mybatisplus

-0.59

POSITIVE LOGITS

 Italijani

0.67

CloseOperation

0.66

 nakalista

0.66

ГЛА

0.61

matchCondition

0.60

httphttps

0.60

frid

0.59

too

0.56

 referenties

0.55

hassee

0.54

Activations Density 0.294%

details related to dialogue and character interactions

No Comments

No Known Activations