INDEX

Explanations

terms that indicate a comparison or relationship between different ideas 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 @ 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

abetes

-0.62

 незавершена

-0.60

 gynhyrchwyd

-0.53

annica

-0.52

 nyingi

-0.52

HasForeignKey

-0.52

stdc

-0.51

ʺ

-0.51

 namelijk

-0.51

 nemlig

-0.49

POSITIVE LOGITS

stateProvider

0.57

Batis

0.54

 ailleurs

0.53

Meanwhile

0.52

wegg

0.51

 Ayrıca

0.50

وقال

0.50

Elsewhere

0.50

 parlant

0.49

Sementara

0.49

Activations Density 0.380%

terms that indicate a comparison or relationship between different ideas or entities

No Comments

No Known Activations