INDEX

Explanations

adverbs and adjectives related to descriptions or classifications in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 muuta

-0.43

ķ

-0.42

gafas

-0.41

 polega

-0.40

 cuantos

-0.40

 gydy

-0.39

 betrokken

-0.38

 pagrind

-0.37

 susun

-0.37

 vandens

-0.36

POSITIVE LOGITS

+#+#

0.98

tagHelperRunner

0.82

rungsseite

0.79

 disponibilités

0.78

setVerticalGroup

0.76

RenderAtEndOf

0.76

 Houſe

0.75

 propOrder

0.75

contentLoaded

0.75

 ujednoznacz

0.75

Activations Density 0.574%

adverbs and adjectives related to descriptions or classifications in scientific contexts

No Comments

No Known Activations