INDEX

Explanations

code elements related to function definitions and imports

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

Python imports

np_acts-logits-general · gemini-2.0-flash

import statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 חיצוניים

-0.63

énario

-0.63

--]

-0.61

сылкі

-0.61

出版年

-0.61

 JpaRepository

-0.57

rungsseite

-0.56

 vectoriales

-0.56

ATUM

-0.55

 uVar

-0.54

POSITIVE LOGITS

 from

0.90

from

0.89

import

0.89

def

0.85

def

0.79

 import

0.68

 "..\..\

0.68

↵

0.62

"""

0.61

basicConfig

0.60

Activations Density 0.054%

code elements related to function definitions and imports

Python imports

import statements

No Comments

No Known Activations