INDEX

Explanations

the word "last" in various contexts, indicating a focus on recent events or time frames

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

Time periods after "last"

np_acts-logits-general · gemini-2.0-flash

last time periods

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 referenties

-0.64

 isInitialized

-0.59

AsUp

-0.58

Vidite

-0.58

@[+][

-0.57

IUrlHelper

-0.57

 Réponses

-0.56

 AssemblyCulture

-0.55

 parseFrom

-0.54

BeginInit

-0.53

POSITIVE LOGITS

 year

0.90

 Friday

0.87

 Thursday

0.85

 Monday

0.84

 Saturday

0.84

 Sunday

0.81

 week

0.81

 Tuesday

0.81

 Wednesday

0.78

 weekend

0.77

Activations Density 0.036%

the word "last" in various contexts, indicating a focus on recent events or time frames

Time periods after "last"

last time periods

No Comments

No Known Activations