INDEX

Explanations

repeated instances of the word "that."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 урна

-0.58

Einzelnachweise

-0.55

focusable

-0.54

rinology

-0.49

tanleria

-0.49

fflush

-0.49

Literatur

-0.49

 retain

-0.47

 Réponses

-0.47

ISO

-0.47

POSITIVE LOGITS

 jenem

0.69

 daß

0.65

Portail

0.65

 jenen

0.60

 complètes

0.59

httphttps

0.58

 PLWABN

0.58

 sanitarias

0.57

AndEndTag

0.56

rmtree

0.56

Activations Density 0.355%

repeated instances of the word "that."

No Comments

No Known Activations