INDEX

Explanations

phrases indicating identity, emotional reactions, or situational contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.41

are

-0.40

-0.39

</h2>

-0.38

bad

-0.38

sur

-0.38

du

-0.38

-0.37

 Paul

-0.37

POSITIVE LOGITS

 propOrder

1.28

 myſelf

1.19

 متعلقه

1.16

 Monfieur

1.00

ſelf

0.99

 Jefus

0.95

Efq

0.94

 itſelf

0.94

ſelves

0.94

 ſche

0.94

Activations Density 0.082%

phrases indicating identity, emotional reactions, or situational contexts

No Comments

No Known Activations