INDEX

Explanations

references to time frames, particularly recent years or decades

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Παραπομπές

-0.55

defer

-0.53

lig

-0.51

ilig

-0.48

kar

-0.46

("")]

-0.45

్రామ

-0.45

 Vish

-0.44

 Manus

-0.44

 competição

-0.44

POSITIVE LOGITS

 lately

1.14

 اخیر

1.09

 recent

1.09

 Lately

1.05

 recently

0.96

recent

0.95

Recent

0.93

 fince

0.90

 reciente

0.89

 Recent

0.88

Activations Density 0.105%

references to time frames, particularly recent years or decades

No Comments

No Known Activations