INDEX

Explanations

references to time-related concepts or measurements

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

 Walkover

-0.55

ایج

-0.49

形の

-0.49

who

-0.47

гих

-0.47

tro

-0.45

Forked

-0.45

 désolés

-0.45

zeiger

-0.45

ToTable

-0.43

POSITIVE LOGITS

 playtime

0.89

Portale

0.87

出版年

0.84

 bedtime

0.74

 heyday

0.73

 Roskov

0.72

XtraBars

0.70

 bloodstream

0.70

 ***!

0.69

 AssemblyCompany

0.68

Activations Density 0.257%

references to time-related concepts or measurements

No Comments

No Known Activations