INDEX

Explanations

phrases and terms related to evaluating conditions, options, and suggestions, particularly focusing on better or safer choices

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 wireType

-0.63

RenderAtEndOf

-0.62

+#+#

-0.59

lapsingToolbar

-0.59

addCriterion

-0.55

 nahilalakip

-0.55

 Biôgrafia

-0.54

期刊论文

-0.53

parsedMessage

-0.53

IVEREF

-0.52

POSITIVE LOGITS

 best

1.98

best

1.75

 safest

1.75

 better

1.70

 preferable

1.69

 melhor

1.61

 mejor

1.59

better

1.57

Best

1.57

 préférable

1.55

Activations Density 0.497%

phrases and terms related to evaluating conditions, options, and suggestions, particularly focusing on better or safer choices

No Comments

No Known Activations