INDEX

Explanations

references to specific locations or geographic features

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

once

-0.45

adin

-0.45

right

-0.43

ად

-0.42

一次

-0.42

cape

-0.41

neman

-0.41

adal

-0.41

vertra

-0.40

adag

-0.40

POSITIVE LOGITS

出版年

0.84

 Majefty

0.74

 myſelf

0.73

 poffe

0.73

 chofe

0.70

 iconTwitter

0.70

 ftate

0.69

 ComVisible

0.68

 purpoſe

0.68

ſelf

0.67

Activations Density 0.441%

references to specific locations or geographic features

No Comments

No Known Activations