INDEX

Explanations

phrases emphasizing the significance or necessity of certain actions or ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ConstraintMaker

-1.05

 nawr

-1.03

 autorytatywna

-1.02

quelize

-0.99

 Majefty

-0.92

 дописавши

-0.87

RenderAtEndOf

-0.87

ValueStyle

-0.86

 препратки

-0.86

tvguidetime

-0.86

POSITIVE LOGITS

to

0.81

 that

0.71

0.54

es

0.53

 people

0.51

for

0.50

the

0.49

0.48

 time

0.47

 bagi

0.47

Activations Density 0.221%

phrases emphasizing the significance or necessity of certain actions or ideas

No Comments

No Known Activations