INDEX

Explanations

references to history and notable events

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

 financières

-0.60

edicated

-0.59

ParentId

-0.56

canActivate

-0.56

[])

-0.55

Necesito

-0.55

runk

-0.54

acabana

-0.54

raad

-0.54

ilich

-0.54

POSITIVE LOGITS

StoryboardSegue

0.55

Демографія

0.53

NewReader

0.53

contentLoaded

0.50

 esternos

0.50

 فريبيس

0.50

GraphicsUnit

0.49

 gili

0.48

Clik

0.47

Портали

0.46

Activations Density 0.489%

references to history and notable events

No Comments

No Known Activations