INDEX

Explanations

comparative phrases that indicate a degree of difference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

bufio

-0.71

CodeAttribute

-0.69

脚注の使い方

-0.67

 softer

-0.61

 Rada

-0.59

xr

-0.58

 Gass

-0.58

 Europeo

-0.58

XA

-0.58

 pars

-0.57

POSITIVE LOGITS

 THAN

0.97

 than

0.91

iastes

0.84

Than

0.77

 Over

0.77

ghalaya

0.73

äher

0.72

THAN

0.72

 Than

0.71

OVER

0.71

Activations Density 0.068%

comparative phrases that indicate a degree of difference

No Comments

No Known Activations