INDEX

Explanations

commands and operations related to data management and manipulation in a programming context

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

preceding or related to "table"

np_acts-logits-general · gemini-2.0-flash

supplemental tables or sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

KommentareTeilen

-0.47

angliski

-0.47

awtextra

-0.46

mphony

-0.45

 héro

-0.45

 noDo

-0.45

corrente

-0.45

--)

-0.43

üyada

-0.42

 AuthService

-0.42

POSITIVE LOGITS

 table

3.87

 Table

3.33

Table

3.21

table

3.19

 tables

2.73

 TABLE

2.49

TABLE

2.44

 Tables

2.32

テーブル

2.20

getTable

2.18

Activations Density 0.193%

commands and operations related to data management and manipulation in a programming context

preceding or related to "table"

supplemental tables or sequences

No Comments

No Known Activations