INDEX

Explanations

key quantitative measurements and variables related to analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

AutoModerator

-0.49

 InputDecoration

-0.46

 Conductor

-0.42

Recognizer

-0.41

 conductor

-0.40

crollView

-0.40

MethodManager

-0.40

ributor

-0.40

 enfans

-0.40

 unresponsive

-0.39

POSITIVE LOGITS

 ویکی‌پدی

0.53

 виправивши

0.52

 Chwiliwch

0.51

angliski

0.51

sbericht

0.51

 autorytatywna

0.49

MigrationBuilder

0.49

RTGC

0.47

 مشين

0.47

Erreferentziak

0.45

Activations Density 0.114%

key quantitative measurements and variables related to analysis

No Comments

No Known Activations