INDEX

Explanations

proper nouns, particularly names and titles related to people or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

+#+#

-0.85

featureID

-0.64

toHaveBeenCalled

-0.63

haustible

-0.61

jahtera

-0.60

 paroisse

-0.60

Sziasztok

-0.60

ophagus

-0.59

RetentionPolicy

-0.58

BASEPATH

-0.58

POSITIVE LOGITS

is

0.56

 also

0.55

ंदीखरीदारी

0.54

 समीक्षाओं

0.50

 started

0.49

 kasarigan

0.47

 Apare

0.47

 همچنین

0.46

 تضيفلها

0.46

 began

0.46

Activations Density 0.381%

proper nouns, particularly names and titles related to people or entities

No Comments

No Known Activations