INDEX

Explanations

dialogue or quotations from characters in a narrative context

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

PerformLayout

-0.65

 الحره

-0.60

BeginInit

-0.55

 ویکی‌پدیا

-0.53

Skocz

-0.52

BeginContext

-0.51

 ujednoznacz

-0.47

出版年

-0.46

mybatisplus

-0.46

RegressionTest

-0.44

POSITIVE LOGITS

 Roman

1.18

Roman

1.03

 Rome

0.98

 Romans

0.96

 ROMAN

0.95

 Caesar

0.93

 roman

0.90

 Roma

0.86

 romana

0.86

Caesar

0.86

Activations Density 0.143%

dialogue or quotations from characters in a narrative context

No Comments

No Known Activations