INDEX

Explanations

references to specific years or temporal indicators within the text

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

 pinulongan

-0.87

dbc

-0.74

 McClellan

-0.69

itecture

-0.69

^^^

-0.69

ならない

-0.68

 cherchés

-0.68

rosia

-0.67

Spurs

-0.67

POSITIVE LOGITS

 year

1.81

 Year

1.64

 YEAR

1.62

year

1.57

Year

1.51

YEAR

1.45

 years

1.30

years

1.20

 année

1.19

 Years

1.14

Activations Density 0.108%

references to specific years or temporal indicators within the text

No Comments

No Known Activations