INDEX

Explanations

modal verbs and negations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

 endforeach

-0.68

Portail

-0.66

 scolaires

-0.60

RTEX

-0.58

apnews

-0.58

viewDidLoad

-0.58

uktur

-0.58

 numberWith

-0.57

sizeCache

-0.56

endphp

-0.55

POSITIVE LOGITS

 consist

0.76

MigrationBuilder

0.71

 consists

0.64

 yield

0.63

 occur

0.62

 yields

0.62

 consisted

0.62

 constitute

0.59

 comprise

0.59

 correspond

0.58

Activations Density 0.818%

modal verbs and negations

No Comments

No Known Activations

modal verbs and negations

No Comments

No Known Activations