INDEX

Explanations

references to Korea and its related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 auffi

-1.25

 avoient

-1.24

 myſelf

-1.23

 pleaſure

-1.23

 ainfi

-1.21

 Monfieur

-1.21

 enfans

-1.17

Efq

-1.16

 ſche

-1.16

 Houſe

-1.16

POSITIVE LOGITS

neg

0.72

 once

0.70

once

0.70

<eos>

0.58

↵↵

0.57

 held

0.56

 even

0.56

in

0.55

Activations Density 0.110%

references to Korea and its related terms

No Comments

No Known Activations