INDEX

Explanations

elements related to formal communication or correspondence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

uxxxx

-0.60

 &___

-0.55

angler

-0.53

tagHelperRunner

-0.53

rova

-0.52

 useState

-0.52

]='\

-0.51

aktery

-0.51

etwork

-0.50

 Anybody

-0.49

POSITIVE LOGITS

 letter

1.03

 lettre

0.98

 letters

0.89

Letter

0.89

 LETTER

0.86

 Letter

0.85

letter

0.80

 lettres

0.78

Dear

0.78

 propOrder

0.75

Activations Density 0.393%

elements related to formal communication or correspondence

No Comments

No Known Activations