INDEX

Explanations

information related to live event results and spoiler warnings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 فريبيس

-0.61

<>());

-0.59

tvguidetime

-0.56

 الرياضيه

-0.55

 виправивши

-0.54

 OnInit

-0.54

تفصیلات

-0.53

_));

-0.52

BeginInit

-0.52

 députés

-0.51

POSITIVE LOGITS

 spoiler

1.14

 spoilers

1.08

Spoilers

0.89

 Spoiler

0.88

spoiler

0.85

 Spoilers

0.85

 SPOILERS

0.79

 SPOILER

0.77

Spoiler

0.77

 spoil

0.77

Activations Density 0.341%

information related to live event results and spoiler warnings

No Comments

No Known Activations