INDEX

Explanations

references to time-related concepts and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

AllowUser

-0.67

 translateY

-0.62

IntoConstraints

-0.61

unnitel

-0.61

 doubtnut

-0.61

Datuak

-0.60

🏾

-0.59

helf

-0.59

 purpoſe

-0.58

 Dlatego

-0.58

POSITIVE LOGITS

 frame

0.94

frame

0.86

frames

0.84

 MonoBehaviour

0.80

 Frame

0.77

 frames

0.77

piece

0.73

liness

0.73

tables

0.70

 period

0.70

Activations Density 0.257%

references to time-related concepts and their implications

No Comments

No Known Activations