INDEX

Explanations

terms related to weight and mass measurements

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

physical weight and mass measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 laſſen

-0.89

oredCriteria

-0.81

<unused41>

-0.73

<unused8>

-0.73

<unused43>

-0.73

<unused47>

-0.73

<unused68>

-0.73

<unused79>

-0.73

[@BOS@]

-0.72

<unused3>

-0.72

POSITIVE LOGITS

 weight

0.85

Weight

0.81

weight

0.81

 Weight

0.76

 WEIGHT

0.68

WEIGHT

0.67

 weigh

0.67

 weighing

0.66

Weigh

0.65

 weights

0.63

Activations Density 0.041%

terms related to weight and mass measurements

physical weight and mass measurements

No Comments

No Known Activations