INDEX

Explanations

quantitative comparisons related to time or amounts

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

that precede approximate time periods

np_acts-logits-general · gemini-2.0-flash

time durations or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 فريبيس

-0.91

 snippetHide

-0.77

 estimés

-0.69

EDEFAULT

-0.68

 OFDb

-0.68

cektir

-0.66

MigrationBuilder

-0.66

+:+

-0.65

writeField

-0.64

saraba

-0.64

POSITIVE LOGITS

 almost

0.77

0.76

 nearly

0.73

 month

0.71

 exactly

0.70

 Exactly

0.66

Almost

0.64

almost

0.64

 Almost

0.63

Exactly

0.61

Activations Density 0.154%

quantitative comparisons related to time or amounts

that precede approximate time periods

time durations or quantities

No Comments

No Known Activations