INDEX

Explanations

phrases related to time and duration in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 hours

-0.70

 Hours

-0.70

Two

-0.66

Two

-0.65

Hours

-0.60

 Deux

-0.58

two

-0.55

hours

-0.55

TWO

-0.54

 horas

-0.53

POSITIVE LOGITS

 fifteen

1.12

ten

1.07

 twenty

0.96

Fifteen

0.93

 Fifteen

0.90

 thirty

0.88

twenty

0.85

 minutes

0.84

Ten

0.84

fif

0.81

Activations Density 0.236%

phrases related to time and duration in various contexts

No Comments

No Known Activations