INDEX

Explanations

segments of code or structure definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

❋

-0.49

 mihi

-0.46

TSR

-0.46

 delas

-0.44

 conquête

-0.44

<bos>

-0.44

 genu

-0.43

 inva

-0.43

 asist

-0.43

 bobs

-0.42

POSITIVE LOGITS

 jspb

0.75

MessageOf

0.64

Tembelea

0.63

BagConstraints

0.61

 iNdEx

0.60

LOYEES

0.60

yii

0.59

setRequest

0.58

̸

0.58

tagHelper

0.57

Activations Density 0.093%

segments of code or structure definitions

No Comments

No Known Activations