INDEX

Explanations

comparative expressions that indicate degrees of comparison

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

 يتيمه

-0.93

 purpoſe

-0.85

 Jefus

-0.79

 ſtate

-0.77

HSP

-0.76

 ftate

-0.75

 Sima

-0.75

 Dolom

-0.74

bufio

-0.74

 Davido

-0.73

POSITIVE LOGITS

 THAN

1.48

 than

1.33

 Than

1.32

Than

1.16

THAN

1.05

than

0.93

OrEqual

0.89

än

0.85

the

0.85

 než

0.82

Activations Density 0.156%

comparative expressions that indicate degrees of comparison

No Comments

No Known Activations