INDEX

Explanations

scientific terms and jargon related to various fields of study

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

nologue

-0.71

ammans

-0.64

はじめに

-0.60

 WebDriverWait

-0.60

ismet

-0.59

nthesis

-0.58

amethasone

-0.57

neapolis

-0.56

 Savoie

-0.56

ibatis

-0.56

POSITIVE LOGITS

DebuggerStep

0.70

+#+#

0.60

TypedDataSet

0.58

ce

0.54

person

0.52

 pareti

0.52

expandindo

0.52

 Hamm

0.52

 '\\;'

0.52

ValueGeneration

0.51

Activations Density 0.546%

scientific terms and jargon related to various fields of study

No Comments

No Known Activations