INDEX

Explanations

references to significant days or events related to specific timelines or occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

nonatomic

-0.56

hintText

-0.56

 cosa

-0.55

SC

-0.54

PCL

-0.53

Advertisement

-0.52

 localObject

-0.52

DebuggerNonUser

-0.51

marle

-0.51

']))

-0.50

POSITIVE LOGITS

day

1.21

DAY

0.91

Day

0.87

day

0.84

 workday

0.84

DAY

0.84

Day

0.80

날

0.80

 night

0.80

День

0.79

Activations Density 0.194%

references to significant days or events related to specific timelines or occurrences

No Comments

No Known Activations