INDEX

Explanations

terms related to conditions and evaluations affecting health and well-being

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

RTDA

-0.40

はじめに

-0.40

bisch

-0.38

protoc

-0.36

汲

-0.35

VOC

-0.34

 quartered

-0.34

पया

-0.34

 ComVisible

-0.34

errHandler

-0.34

POSITIVE LOGITS

 extremes

0.58

过度

0.57

 exceso

0.57

RenderAtEndOf

0.57

 excessive

0.56

 tantôt

0.54

 navideñas

0.52

 >=",

0.52

 excesso

0.52

 Excessive

0.50

Activations Density 0.672%

terms related to conditions and evaluations affecting health and well-being

No Known Activations