INDEX

Explanations

terms related to occupational safety and health regulations

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

Statements about toxicity

np_acts-logits-general · gemini-2.0-flash

toxicity and related studies

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

jsxFileName

-0.55

↵

-0.42

</em>

-0.40

-0.39

ir

-0.37

-0.36

 Leistung

-0.36

POSITIVE LOGITS

 متعلقه

0.93

 للاسماء

0.89

脚注の使い方

0.88

 مرئيه

0.85

principalTable

0.85

 vPvB

0.85

 Савезне

0.81

 greateſt

0.79

 Normdatei

0.79

Autoritní

0.78

Activations Density 0.075%

terms related to occupational safety and health regulations

Statements about toxicity

toxicity and related studies

No Comments

No Known Activations