INDEX

Explanations

numerical values or statistics related to decades or periods of time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

-0.69

 Samo

-0.69

 Krä

-0.67

عر

-0.67

 aproximada

-0.67

urka

-0.66

 Rama

-0.66

 initWithFrame

-0.66

tivism

-0.66

 pira

-0.66

POSITIVE LOGITS

1.45

+#+#

0.90

TEN

0.85

 Tenth

0.84

 Tencent

0.84

Ten

0.83

Ten

0.82

getKeyCode

0.81

Loh

0.80

Activations Density 0.299%

numerical values or statistics related to decades or periods of time

No Comments

No Known Activations