INDEX

Explanations

phrases that indicate necessity or point out the importance of actions or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

IVEREF

-0.86

 esternos

-0.71

 poffe

-0.68

addCriterion

-0.64

 oprot

-0.62

 виправивши

-0.60

ázaro

-0.60

 autorytatywna

-0.60

Jereo

-0.58

PyExc

-0.58

POSITIVE LOGITS

 Нужно

0.83

 faut

0.83

 bisogna

0.81

 Надо

0.78

 perlu

0.77

Надо

0.76

 trzeba

0.74

 occorre

0.73

 należy

0.72

 следует

0.72

Activations Density 0.410%

phrases that indicate necessity or point out the importance of actions or concepts

No Comments

No Known Activations