INDEX

Explanations

phrases indicating cause and effect or legal consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

Джерела

-0.51

/******/

-0.43

indicato

-0.42



-0.42

ГЛА

-0.41

Portail

-0.41

EMBER

-0.41

あんな

-0.40

че

-0.40

("")]

-0.38

POSITIVE LOGITS

HomeAsUpEnabled

0.69

 ويكيميديا

0.67

RenderAtEndOf

0.64

onAttach

0.64

ReusableCell

0.64

+#+#

0.63

FTFY

0.63

Saluti

0.61

 happen

0.60

AndEndTag

0.59

Activations Density 0.577%

phrases indicating cause and effect or legal consequences

No Comments

No Known Activations