INDEX

Explanations

references to character encoding formats, specifically UTF encoding types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<eos>

-0.69

#+#

-0.65

 zile

-0.64

FailureListener

-0.63

strokeStyle

-0.62

ⓧ

-0.59

-0.58

 relâche

-0.57

 jours

-0.57

例句

-0.56

POSITIVE LOGITS

UTF

2.63

UTF

1.81

utf

1.41

utf

1.35

Utf

1.15

bibfield

0.87

Utf

0.82

 nahilalakip

0.75

>\<^

0.75

لينكات

0.75

Activations Density 0.017%

references to character encoding formats, specifically UTF encoding types

No Comments

No Known Activations