INDEX

Explanations

words related to specific substances, potentially in a scientific or medical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 typelib

-0.89

AddTagHelper

-0.80

tagHelperRunner

-0.75

UnitTesting

-0.74

PrototypeOf

-0.65

IsContent

-0.65

LookAnd

-0.64

InSection

-0.64

InvalidProtocol

-0.64

 Taktlose

-0.63

POSITIVE LOGITS

にかけて

0.49

참고

0.49

Jährige

0.48

 发表于

0.47

WebServlet

0.47

insula

0.46

ANIEL

0.46

colage

0.44

{§

0.44

Activations Density 1.145%

words related to specific substances, potentially in a scientific or medical context

No Comments

No Known Activations