INDEX

Explanations

references to flags and their symbolic significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

:✨

-0.76

verifyException

-0.67

 שוליים

-0.64

Carriera

-0.62

Rujuakan

-0.61

Trayectoria

-0.60

Bioaccumulative

-0.57

QMetaType

-0.57

ględ

-0.56

providedIn

-0.54

POSITIVE LOGITS

 flag

1.24

 flags

1.24

 Flag

1.14

 drapeau

1.09

flag

1.05

 bendera

1.04

Flag

1.03

 FLAG

1.02

 Drapeau

1.01

 Flags

0.98

Activations Density 0.316%

references to flags and their symbolic significance

No Comments

No Known Activations