INDEX

Explanations

ideas related to safety and health risks in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

the

-0.99

-0.87

it

-0.76

its

-0.73

not

-0.73

-0.72

-0.70

 this

-0.70

POSITIVE LOGITS

 AssemblyCulture

0.85

 anún

0.77

 GenerationType

0.75

CodeAttribute

0.75

 mauva

0.73

BagLayout

0.71

TargetException

0.68

 tartalomajánló

0.67

 wikipagina

0.65

 NSCoder

0.65

Activations Density 0.456%

ideas related to safety and health risks in various contexts

No Comments

No Known Activations