INDEX

Explanations

numerical data and related formatting throughout the text

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

Tokens before ".jpg" file extensions

np_acts-logits-general · gemini-2.0-flash

citations and references

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

FieldDescriptor

-0.61

зулта

-0.57

надцать

-0.52

 FishBase

-0.52

Compartir

-0.51

rsc

-0.51

 LCCN

-0.48

 blijkt

-0.48

TryGetValue

-0.47

FileDescriptor

-0.47

POSITIVE LOGITS

########.

0.73

 ExecuteAsync

0.65

 MainAxisSize

0.61

expandindo

0.59

ValueStyle

0.59

 оригіналу

0.59

KURZBESCHREIBUNG

0.57

 premature

0.57

Qualitative

0.56

BorderFactory

0.56

Activations Density 0.394%

numerical data and related formatting throughout the text

Tokens before ".jpg" file extensions

citations and references

No Comments

No Known Activations