INDEX

Explanations

phrases indicating prevalence or quantification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

原始内容存档于

-0.66

UnusedPrivate

-0.52

 wanted

-0.48

HOT

-0.48

ToLeft

-0.48

as

-0.47

 الض

-0.47

مق

-0.47

 مق

-0.46

Hozzáférés

-0.46

POSITIVE LOGITS

ſelf

0.94

 pleaſure

0.94

 Jefus

0.92

 itſelf

0.92

 greateſt

0.91

 purpoſe

0.87

 beſt

0.86

 poffible

0.86

 ſtre

0.85

 tranſ

0.85

Activations Density 0.232%

phrases indicating prevalence or quantification

No Comments

No Known Activations