INDEX

Explanations

references to coding elements and markup or structure in programming languages

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

 betweenstory

-0.76

 MainAxisSize

-0.72

 BorderSide

-0.72

 kasarigan

-0.68

 BoxFit

-0.65

TargetException

-0.63

PreferredItem

-0.63

.[/

-0.62

 المعيارى

-0.62

 ProtoMessage

-0.62

POSITIVE LOGITS

↵

0.65

#+#

0.62

MigrationBuilder

0.60

span

0.56

пода

0.56

mstyle

0.54

pan

0.53

ๆ

0.51

 ayer

0.51

rowad

0.50

Activations Density 0.045%

references to coding elements and markup or structure in programming languages

No Comments

No Known Activations