INDEX

Explanations

references to time, specifically years and months

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 bParam

-0.61

 Intensive

-0.60

Abp

-0.58

PHIA

-0.58

 تضيفلها

-0.57

intensive

-0.57

Abp

-0.57

 titolata

-0.57

codecs

-0.56

 intensive

-0.56

POSITIVE LOGITS

Year

0.87

YEAR

0.69

gonic

0.66

year

0.64

ArrowToggle

0.61

featureID

0.61

 Year

0.59

 year

0.59

legg

0.59

 YEAR

0.57

Activations Density 0.303%

references to time, specifically years and months

No Comments

No Known Activations