INDEX

Explanations

instances of the word "match" and related terms in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 généraux

-0.52

ラク

-0.52

 nakalista

-0.51

ए

-0.50

ménage

-0.49

 ferma

-0.49

 månader

-0.49

 माध्यम

-0.47

jois

-0.47

iad

-0.47

POSITIVE LOGITS

 wits

0.92

stick

0.87

sticks

0.85

maker

0.74

UpInside

0.72

tvguidetime

0.70

uxxxx

0.68

 mẽ

0.68

 OMIT

0.67

 AppColors

0.66

Activations Density 0.060%

instances of the word "match" and related terms in various contexts

No Comments

No Known Activations