INDEX

Explanations

names and terms associated with notable individuals and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

complexContent

-0.90

styleType

-0.86

IntoConstraints

-0.81

:✨

-0.75

клопе

-0.74

fillType

-0.74

 CiNii

-0.73

 typelib

-0.73

apimachinery

-0.72

__":

-0.72

POSITIVE LOGITS

<u>

0.60

р

0.55

zydent

0.54

ALITY

0.54

 vero

0.53

ality

0.52

ieri

0.52

losis

0.51

 Premiership

0.51

 Schilling

0.51

Activations Density 0.494%

names and terms associated with notable individuals and entities

No Comments

No Known Activations