INDEX

Explanations

references to governmental or organizational entities

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

MLLoader

-0.47

 насељу

-0.41

MigrationBuilder

-0.41

WriteAttribute

-0.37

 mats

-0.35

 newBuilder

-0.34

Personensuche

-0.34

 JpaRepository

-0.33

ffilm

-0.33

som

-0.33

POSITIVE LOGITS

 Behör

0.60

 juſ

0.59

 bureauc

0.57

 federal

0.56

 eſſ

0.54

 presid

0.52

Eſ

0.51

 Bureau

0.51

tagHelperRunner

0.50

 agency

0.48

Activations Density 0.267%

references to governmental or organizational entities

No Comments

No Known Activations