INDEX

Explanations

numerical values and their associated meanings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Nicholls

-0.70

อ้างอิง

-0.66

Pá

-0.65

ütfen

-0.64

glColor

-0.63

PCC

-0.63

buri

-0.63

rrggbb

-0.62

 חיצוניים

-0.62

 López

-0.62

POSITIVE LOGITS

βολ

0.73

MockBean

0.70

AllowUser

0.70

 Majefty

0.70

HW

0.67

 Medea

0.64

racene

0.62

altham

0.62

 midline

0.60

annica

0.60

Activations Density 0.342%

numerical values and their associated meanings

No Comments

No Known Activations