INDEX

Explanations

references to months and month-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

isticated

-0.71

 trúc

-0.70

Swa

-0.69

-0.66

lidene

-0.65

(',')

-0.65

 wieś

-0.64

JEE

-0.63

agra

-0.62

rfan

-0.61

POSITIVE LOGITS

 month

1.57

 Month

1.51

 months

1.37

month

1.35

 MONTH

1.35

MONTH

1.32

 Months

1.31

months

1.26

 MONTHS

1.18

Months

1.17

Activations Density 0.054%

references to months and month-related concepts

No Comments

No Known Activations