INDEX

Explanations

references to the current state or relevance of concepts over time

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

Acerca

-0.54

 للمعارف

-0.54

geber

-0.53

JvmStatic

-0.53

Referencie

-0.52

 mostrarán

-0.51

تقاوى

-0.50

">'.$

-0.49

":

-0.49

MarshalTo

-0.49

POSITIVE LOGITS

now

0.79

now

0.77

IUrlHelper

0.72

 ahora

0.61

HtmlAttribute

0.60

 SUDOC

0.60

setVerticalGroup

0.58

 aujourd

0.57

AnchorTagHelper

0.56

 tutt

0.56

Activations Density 0.340%

references to the current state or relevance of concepts over time

No Comments

No Known Activations