INDEX

Explanations

references to absence or lack

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 Cæsar

-0.96

 Monfieur

-0.83

ſelf

-0.74

ője

-0.73

 ſhe

-0.70

 quoque

-0.70

 eléctricas

-0.69

 purpoſe

-0.69

 розта

-0.68

 ſon

-0.68

POSITIVE LOGITS

 Without

1.97

 without

1.95

without

1.90

Without

1.90

 WITHOUT

1.74

WITHOUT

1.73

Ohne

1.70

 ohne

1.58

 senza

1.51

 zonder

1.47

Activations Density 0.102%

references to absence or lack

No Comments

No Known Activations