INDEX

Explanations

quantitative time references, particularly related to months and weeks

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RTEX

-0.71

Obrázky

-0.65

hood

-0.61

:✨

-0.59

 Insee

-0.59

 обе

-0.57

 NEIGH

-0.54

Демографія

-0.54

principalTable

-0.53

 neigh

-0.53

POSITIVE LOGITS

 months

0.97

months

0.92

 Months

0.90

Months

0.86

 MONTHS

0.80

 meses

0.77

 GenerationType

0.73

TabStop

0.69

 Monate

0.68

 maanden

0.65

Activations Density 0.120%

quantitative time references, particularly related to months and weeks

No Comments

No Known Activations