INDEX

Explanations

phrases emphasizing assessment or evaluation of facts and claims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 propOrder

-0.65

TagMode

-0.59

expandindo

-0.57

 doInBackground

-0.54

GIVEREF

-0.53

 FetchType

-0.49

IUrlHelper

-0.49

UnitTesting

-0.46

IsContent

-0.45

simpleType

-0.45

POSITIVE LOGITS

Synonymes

0.45

alagi

0.44

AutoScale

0.41

 immerhin

0.40

Recall

0.40

 ooit

0.40

attuale

0.40

 recall

0.40

そういえば

0.40

 none

0.39

Activations Density 0.730%

phrases emphasizing assessment or evaluation of facts and claims

No Comments

No Known Activations