INDEX

Explanations

references to fire or related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

+#+

-0.81

FormTagHelper

-0.75

 estimés

-0.72

 nødvendig

-0.68

帖最后由

-0.67

 nødven

-0.64

RectangleBorder

-0.62

 compless

-0.61

клопе

-0.61

ConstraintMaker

-0.60

POSITIVE LOGITS

 fire

2.92

 fires

2.89

fire

2.73

 Fire

2.72

Fire

2.68

 FIRE

2.43

FIRE

2.42

fires

2.41

 Fires

2.35

 fired

2.11

Activations Density 0.103%

references to fire or related concepts

No Comments

No Known Activations