INDEX

Explanations

occurrences of the word "info" and its variations in different contexts

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

"info" followed by punctuation or code-related terms

np_acts-logits-general · gemini-2.0-flash

info type and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ly

-0.64

Wal

-0.62

 Wilber

-0.62

 Hare

-0.61

 Adela

-0.59

 Soler

-0.57

Discografia

-0.56

 Daven

-0.56

 Hammers

-0.56

 Roper

-0.54

POSITIVE LOGITS

 getInfo

1.35

 infos

1.33

 Info

1.24

 info

1.21

INFO

1.16

 Infos

1.16

infos

1.14

 INFO

1.13

fileInfo

1.09

PageInfo

1.08

Activations Density 0.033%

occurrences of the word "info" and its variations in different contexts

"info" followed by punctuation or code-related terms

info type and data structures

No Comments

No Known Activations