INDEX

Explanations

expressions of uncertainty and expectation

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

Negative Logits

 Desire

-0.47

modo

-0.46

 CURLOPT

-0.46

huo

-0.45

AGUA

-0.45

 termes

-0.44

 tava

-0.43

жела

-0.43

Dort

-0.42

 preliminar

-0.42

POSITIVE LOGITS

DockStyle

1.09

 يتيمه

0.83

IntoConstraints

0.81

featureID

0.79

 beginnetje

0.74

 Poul

0.73

 someday

0.71

WebElementEntity

0.68

المناصب

0.68

AnchorStyles

0.68

Activations Density 0.290%

expressions of uncertainty and expectation

No Known Activations