INDEX

Explanations

references to legal terms and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 annual

-0.70

 quarterly

-0.64

 monthly

-0.63

 weekly

-0.61

 yearly

-0.61

 QName

-0.58

 daily

-0.58

annual

-0.58

 protoimpl

-0.57

 nightly

-0.57

POSITIVE LOGITS

skjaer

0.63

ecake

0.54

styleType

0.51

RectangleBorder

0.50

 Rivière

0.49

ramiento

0.46

BoxLayout

0.46

tesy

0.46

 оригіналу

0.46

êque

0.45

Activations Density 1.351%

references to legal terms and processes

No Comments

No Known Activations