INDEX

Explanations

forms of indicating or signaling information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ArgsConstructor

-0.60

usercontent

-0.59

 Saltar

-0.59

 Lippen

-0.58

nossa

-0.57

صدار

-0.56

 abrazo

-0.55

 administers

-0.54

 Audiodateien

-0.54

chable

-0.54

POSITIVE LOGITS

 INDIC

1.35

 indicate

1.31

 indicating

1.31

 suggesting

1.26

 indicates

1.26

 indicated

1.23

 suggest

1.22

 indications

1.21

 suggests

1.19

 hinting

1.18

Activations Density 0.302%

forms of indicating or signaling information

No Comments

No Known Activations