INDEX

Explanations

negative expressions and sentiments related to disappointment or detriment

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

-0.48

-0.39

 process

-0.38

↵

-0.37

ことから

-0.37

 kesempatan

-0.36

บาล

-0.35

<bos>

-0.35

can

-0.34

POSITIVE LOGITS

tvguidetime

0.94

脚注の使い方

0.85

 detriment

0.83

 BoxFit

0.79

^(@)

0.79

+#+#

0.78

ValueGenerated

0.77

ंदीखरीदारी

0.77

%")

0.74

 facie

0.74

Activations Density 0.146%

negative expressions and sentiments related to disappointment or detriment

No Comments

No Known Activations