INDEX

Explanations

phrases related to time, specifically measurements of hours

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

[]){

-0.65

****************

-0.64

璨

-0.62

 mellitus

-0.61

 encontra

-0.61

dab

-0.60

eld

-0.60

,))

-0.60

noli

-0.59

)),

-0.59

POSITIVE LOGITS

 hours

2.02

 Hours

1.90

 HOURS

1.85

hours

1.84

 HOUR

1.80

 hour

1.79

HOURS

1.76

 Hour

1.74

Hours

1.66

hour

1.63

Activations Density 0.089%

phrases related to time, specifically measurements of hours

No Comments

No Known Activations