INDEX

Explanations

time-related measurements and references

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

NameInMap

-0.66

 Normdatei

-0.58

strada

-0.57

 kaynağından

-0.56

PreferredItem

-0.56

Enllaces

-0.55

Skocz

-0.54

("}\

-0.54

 يتيمه

-0.53

Footnote

-0.53

POSITIVE LOGITS

 minutes

1.28

 minute

1.25

 seconds

1.22

minutes

1.19

 MINUTE

1.17

minute

1.14

Minute

1.14

Minutes

1.14

 Minutes

1.13

 minutos

1.13

Activations Density 0.238%

time-related measurements and references

No Comments

No Known Activations