INDEX

Explanations

references to data points or highlighting points of interest

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Theſe

-0.92

Autoritní

-0.89

 DELLE

-0.88

ChildScrollView

-0.85

ſelf

-0.78

 MainAxisSize

-0.78

 onCancelled

-0.77

 yoksa

-0.72

 Majefty

-0.72

 Barbier

-0.72

POSITIVE LOGITS

 POINT

2.29

 point

2.29

point

2.22

 points

2.18

 Point

2.15

Point

2.08

POINT

2.07

points

1.99

 Points

1.94

 POINTS

1.89

Activations Density 0.065%

references to data points or highlighting points of interest

No Comments

No Known Activations