INDEX

Explanations

punctuation marks and formatting characters

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

argout

-0.90

AndEndTag

-0.87

 يتيمه

-0.84

脚注の使い方

-0.79

Hozzáférés

-0.79

NameInMap

-0.77

InputBorder

-0.76

 GenerationType

-0.75

CrossRef

-0.74

 فريبيس

-0.73

POSITIVE LOGITS

simus

0.55

 coach

0.53

(',');

0.52

isseurs

0.51

 sẻ

0.49

二是

0.47

انة

0.46

Samo

0.46

зий

0.45

象

0.45

Activations Density 0.563%

punctuation marks and formatting characters

No Comments

No Known Activations