INDEX

Explanations

elements related to technical and regulatory language

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

########.

-0.61

 quæ

-0.60

 Kitch

-0.60

ignty

-0.58

UGHTER

-0.57

éndole

-0.56

 Chúng

-0.56

.$_

-0.56

 Vikipedi

-0.55

eterangan

-0.53

POSITIVE LOGITS

Билгалдахарш

0.87

EndContext

0.76

 الحره

0.76

はじめに

0.69

terase

0.67

ViewInit

0.65

ⓘ

0.65



0.63

PRNewswire

0.62

usermodel

0.62

Activations Density 1.202%

elements related to technical and regulatory language

No Comments

No Known Activations