INDEX

Explanations

references to verbs and events, particularly in the context of grammatical and semantic labeling

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 EconPapers

-0.80

 OFDb

-0.78

 дописавши

-0.76

 صوتيه

-0.68

 estimés

-0.66

PhysRevLett

-0.63

 مشين

-0.62

UnsafeEnabled

-0.59

RenderAtEndOf

-0.58

LookAnd

-0.57

POSITIVE LOGITS

 itſelf

0.78

 ſta

0.78

 ſch

0.75

ſelves

0.74

 unſ

0.74

 faſt

0.73

 leſs

0.71

aſ

0.71

 ſte

0.71

 paſſ

0.70

Activations Density 0.691%

references to verbs and events, particularly in the context of grammatical and semantic labeling

No Comments

No Known Activations