INDEX

Explanations

references to dates and time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

dics

-0.58

gson

-0.57

ModelForm

-0.57

Pyx

-0.55

mannian

-0.53

ος

-0.53

CharField

-0.53

Noun

-0.52

shiro

-0.52

mphony

-0.52

POSITIVE LOGITS

 date

2.47

 dates

2.27

 Dates

2.01

 Date

2.00

 DATE

1.92

 dated

1.91

 dating

1.88

 DATES

1.84

dating

1.81

dates

1.80

Activations Density 0.067%

references to dates and time periods

No Comments

No Known Activations