INDEX

Explanations

references to systems, particularly in contexts related to stability and complexity

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ScopeManager

-0.75

SourceChecksum

-0.73

IntoConstraints

-0.68

ThroughAttribute

-0.66

اریخ

-0.63

 parlar

-0.62

ьаж

-0.62

 differenza

-0.61

CreateMap

-0.59

lasty

-0.59

POSITIVE LOGITS

 system

1.86

 systems

1.67

 System

1.63

 SYSTEM

1.57

system

1.56

 sistema

1.50

systems

1.50

 Systems

1.49

System

1.47

SYSTEM

1.43

Activations Density 0.667%

references to systems, particularly in contexts related to stability and complexity

No Comments

No Known Activations