INDEX

Explanations

references to system components in code or documentation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Espèce

-0.69

Amicalement

-0.65

fjspx

-0.65

 Drapeau

-0.62

\{\\

-0.59

ophone

-0.57

BeginContext

-0.57

)|^{

-0.56

Abb

-0.56

Javadoc

-0.55

POSITIVE LOGITS

System

1.73

system

1.15

 system

1.12

 System

1.12

 SYSTEM

0.91

 systeem

0.89

SYSTEM

0.89

系统

0.85

ystem

0.84

 sistem

0.81

Activations Density 0.013%

references to system components in code or documentation

No Comments

No Known Activations