INDEX

Explanations

expressions related to personal opinions and beliefs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

RegistryLite

-0.77

 Roskov

-0.77

tvguidetime

-0.69

 &___

-0.67

Попис

-0.66

例文帳に追加

-0.65

脚注の使い方

-0.64

তথ্যসূত্র

-0.64

 protoimpl

-0.63

mybatisplus

-0.62

POSITIVE LOGITS

>>()

0.56

')):

0.47

[__

0.47

 Piccolo

0.47

 том

0.46

Fim

0.45

NU

0.45

FXML

0.43

()].

0.43

TID

0.43

Activations Density 0.043%

expressions related to personal opinions and beliefs

No Comments

No Known Activations