INDEX

Explanations

terms related to JSON data formatting and manipulation

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

ghijklmnop

-0.56

rishnan

-0.51

 dilan

-0.51

lotti

-0.50

ordnung

-0.49

 зовут

-0.48

lynol

-0.48

gänger

-0.48

 commerces

-0.48

seiti

-0.48

POSITIVE LOGITS

rpc

0.74

 հղումներ

0.73

expandindo

0.64

webtoken

0.64

djangoproject

0.64

 للمعارف

0.62

APORE

0.62

mphony

0.61

 protoimpl

0.60

PointerException

0.60

Activations Density 0.083%

terms related to JSON data formatting and manipulation

No Comments

No Known Activations