INDEX

Explanations

expressions of preference and enjoyment

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

 Asher

-0.70

<h6>

-0.69

ExecuteReader

-0.68

MockBean

-0.68

 brazos

-0.67

èvre

-0.65

 Crowe

-0.64

রণ

-0.64

ZEL

-0.63

 Brant

-0.63

POSITIVE LOGITS

 liked

1.40

 liking

1.27

 Liked

1.25

 likes

1.24

 Likes

1.22

likes

1.14

dislike

1.14

liked

1.11

Likes

1.10

 gusta

1.08

Activations Density 0.062%

expressions of preference and enjoyment

No Comments

No Known Activations