INDEX

Explanations

ellipses and variations of them

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

letoe

-0.49

Movie

-0.44

bl

-0.43

aver

-0.43

 brand

-0.41

 نق

-0.41

影

-0.41

WebElementEntity

-0.40

di

-0.40

 Movie

-0.39

POSITIVE LOGITS

tvguidetime

1.02

 snippetHide

0.93

AddTagHelper

0.85



0.80

ABUL

0.79

 hashCode

0.79

Datuak

0.78

ArgsConstructor

0.76

ThemeOverlay

0.76

__':

0.74

Activations Density 0.049%

ellipses and variations of them

No Comments

No Known Activations