INDEX

Explanations

proper nouns, specifically names of people

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 kasarigan

-0.62

Rüyada

-0.62

expandindo

-0.60

Geplaatst

-0.60

 validamos

-0.58

بوابة

-0.58

 للاسماء

-0.57

 complètes

-0.56

 lontano

-0.55

 betreft

-0.55

POSITIVE LOGITS

cepan

0.58

olithic

0.55

 jsonify

0.53

'&:

0.53

GIVEREF

0.52

posedge

0.52

▼

0.51

ArgsConstructor

0.51

CAUTIONS

0.50

}{*}{

0.50

Activations Density 2.080%

proper nouns, specifically names of people

No Comments

No Known Activations