INDEX

Explanations

expressions of curiosity or wonder about various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

つもり

-0.34

对不起

-0.31

MoveNext

-0.31

.}}

-0.30

 sengaja

-0.30

سرائيلي

-0.30

اث

-0.29

imanapun

-0.29

hamdulillah

-0.29

RemoveAt

-0.29

POSITIVE LOGITS

 wonder

2.19

 wondered

2.13

 wondering

2.13

 question

2.02

wonder

1.98

 Wonder

1.76

 wonders

1.73

question

1.70

Wonder

1.64

Wondering

1.58

Activations Density 0.577%

expressions of curiosity or wonder about various subjects

No Comments

No Known Activations