INDEX

Explanations

references to time-related concepts or data

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 виправивши

-1.07

Autoritní

-0.95

 nahilalakip

-0.88

 فريبيس

-0.83

']")

-0.81

ReusableCell

-0.81

^(@)

-0.79

IBOutlet

-0.77

 tartalomajánló

-0.74

 مشين

-0.74

POSITIVE LOGITS

time

1.45

Time

1.41

TIME

1.28

 Time

1.24

 getTime

1.22

 TIME

1.16

getTime

1.14

setTime

1.10

times

1.09

 time

1.05

Activations Density 0.099%

references to time-related concepts or data

No Comments

No Known Activations