INDEX

Explanations

relationships between individuals, particularly in reference to groups or collectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

LEncoder

-0.64

PickerController

-0.63

InjectAttribute

-0.61

timation

-0.60

تقاوى

-0.58

󠁢

-0.58

actylus

-0.54

apunov

-0.52

didSet

-0.52

oneph

-0.52

POSITIVE LOGITS

 members

0.87

 gathered

0.82

members

0.71

 pamoja

0.68

們

0.63

全員

0.62

 collectively

0.59

 together

0.58

бята

0.58

 tụ

0.57

Activations Density 0.338%

relationships between individuals, particularly in reference to groups or collectives

No Comments

No Known Activations