INDEX

Explanations

references to specific reports or incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

principalColumn

-0.58

 صوتيه

-0.57

 AssemblyProduct

-0.56

 alluminio

-0.56

 pouss

-0.55

 femininas

-0.54

Gön

-0.53

 BoxDecoration

-0.53

WaitGroup

-0.53

ByExample

-0.53

POSITIVE LOGITS

Elsewhere

0.82

Meanwhile

0.73

 Elsewhere

0.72

 betweenstory

0.67

 Meanwhile

0.66

djangoproject

0.64

 meanwhile

0.63

 Continuing

0.62

 updates

0.62

 continuing

0.61

Activations Density 0.222%

references to specific reports or incidents

No Comments

No Known Activations