INDEX

Explanations

references to various types of abilities and capabilities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.49

Ly

-0.48

もしれない

-0.48

TO

-0.48

To

-0.48

si

-0.48

-0.47

менный

-0.47

ならない

-0.47

POSITIVE LOGITS

 Мексичка

1.06

kháu

1.03

хьтан

1.00

 AssemblyCulture

0.99

 defaultstate

0.97

 itſelf

0.94

✨:

0.94

 NSCoder

0.94

istoitu

0.93

 poffible

0.92

Activations Density 0.239%

references to various types of abilities and capabilities

No Comments

No Known Activations