INDEX

Explanations

terms related to changes, particularly increases or decreases in metrics over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 future

-0.42

 буду

-0.42

 univers

-0.41

фу

-0.41

-0.40

run

-0.40

 archive

-0.39

As

-0.39

 Dist

-0.39

 бу

-0.39

POSITIVE LOGITS

ViewFeatures

1.00

abestanden

0.97

 itſelf

0.96

MigrationBuilder

0.94

OGND

0.92

EndContext

0.91

 mudou

0.91

webElementXpaths

0.91

IsMutable

0.90

 AssemblyCulture

0.89

Activations Density 0.428%

terms related to changes, particularly increases or decreases in metrics over time

No Comments

No Known Activations