INDEX

Explanations

elements related to programming and email headers

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

Newline characters and related formatting

np_acts-logits-general · gemini-2.0-flash

newline and carriage return

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

Życiorys

-0.60

%)$

-0.58

%"),

-0.56

AddTagHelper

-0.56

cipes

-0.55

 AssemblyProduct

-0.55

iredo

-0.55

Geplaatst

-0.54

پیوند

-0.53

cerpt

-0.51

POSITIVE LOGITS

 newline

0.87

"\

0.86

 endl

0.81

("\

0.76

'\

0.74

endl

0.74

newLine

0.74

newline

0.71

 line

0.70

LINE

0.68

Activations Density 0.249%

elements related to programming and email headers

Newline characters and related formatting

newline and carriage return

No Comments

No Known Activations