INDEX

Explanations

information related to specific elements, features, or metrics in various contexts such as gaming, molecular biology, and media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

toHaveBeenCalled

-0.63

GraphicsUnit

-0.58

 intptr

-0.58

:✨

-0.53

 Spal

-0.53

gway

-0.50

 SimpleName

-0.49

chauer

-0.49

érique

-0.49

phe

-0.49

POSITIVE LOGITS

 MainAxisSize

0.57

 dotenv

0.55

 SqlCommand

0.54

CodedInputStream

0.49

setVerticalGroup

0.49

conio

0.48

msgTypes

0.48

JspWriter

0.47

WebpackPlugin

0.47

 betweenstory

0.47

Activations Density 2.116%

information related to specific elements, features, or metrics in various contexts such as gaming, molecular biology, and media

No Comments

No Known Activations