INDEX

Explanations

proper nouns, particularly names of individuals or entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SBATCH

-0.70

PreferredItem

-0.65

 насељу

-0.62

oretical

-0.61

 tahan

-0.58

selaer

-0.55

 useParams

-0.55

 Thule

-0.55

Manbalar

-0.53

Havolalar

-0.53

POSITIVE LOGITS

RenderAtEndOf

0.58

rawDesc

0.46

WebVitals

0.42

Ir

0.42

 Dés

0.42

 Enfin

0.42

InvalidProtocol

0.41

แฟ

0.41

estan

0.40

 Jungen

0.40

Activations Density 1.128%

proper nouns, particularly names of individuals or entities

No Comments

No Known Activations