INDEX

Explanations

terms related to a preferred neutral classification

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

 altrett

-0.79

 EconPapers

-0.75

InjectAttribute

-0.72

 ſame

-0.72

NUMX

-0.71

 Normdatei

-0.70

 purpoſe

-0.70

ंदीखरीदारी

-0.68

Datuak

-0.67

 ſeveral

-0.67

POSITIVE LOGITS

 least

0.64

 preferred

0.59

 best

0.59

ที่สุด

0.58

 Preferred

0.54

 compromise

0.54

 adopted

0.53

 preferable

0.53

 prefer

0.52

Preferred

0.51

Activations Density 0.771%

terms related to a preferred neutral classification

No Comments

No Known Activations