INDEX

Explanations

terms and phrases related to "confounding" or "conflict" in various contexts

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

starting with "Conf" related to configuration or conflict

np_acts-logits-general · gemini-2.0-flash

Conf followed by verb/adjective endings

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Portale

-0.74

 actionPerformed

-0.65

enterOuterAlt

-0.65

 grecque

-0.59

ielli

-0.58

Vidite

-0.57

lads

-0.57

 đây

-0.57

TacToe

-0.56

+#+#

-0.56

POSITIVE LOGITS

setVerticalGroup

0.57

řízení

0.56

 conf

0.56

urator

0.54

ration

0.54

0.53

 '../../../

0.51

 Conf

0.51

.*")]

0.51

ReusableCell

0.49

Activations Density 0.128%

terms and phrases related to "confounding" or "conflict" in various contexts

starting with "Conf" related to configuration or conflict

Conf followed by verb/adjective endings

No Comments

No Known Activations