INDEX

Explanations

references to penalties and the conditions under which they are imposed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 surla

-0.74

StoryboardSegue

-0.66

ulemon

-0.63

vaux

-0.62

onViewCreated

-0.62

 attiv

-0.60

améli

-0.60

 bäst

-0.59

zeiro

-0.59

ьа

-0.57

POSITIVE LOGITS

 penalty

2.51

 penalties

2.31

 Penalty

2.15

 punishment

2.07

 Penalties

2.05

penalty

2.02

 penal

1.87

Penalty

1.85

 punish

1.81

 punishments

1.72

Activations Density 0.152%

references to penalties and the conditions under which they are imposed

No Comments

No Known Activations