INDEX

Explanations

temporal references indicating recent events or time periods

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

Hentet

-1.01

 Roskov

-0.81

IsContent

-0.80

 Superhost

-0.69

RODUZIONE

-0.69

انگلیسی

-0.69

 FontWeight

-0.68

AccessorTable

-0.68

ConstraintMaker

-0.68

.}~\

-0.67

POSITIVE LOGITS

 disambiguazione

0.54

0.51

 Walkover

0.49

Diweddarwch

0.48

 because

0.47

ViewFeatures

0.47

Linq

0.44

Scaler

0.44

 tempore

0.43

Activations Density 0.269%

temporal references indicating recent events or time periods

No Comments

No Known Activations