INDEX

Explanations

references to key roles and positions within organizations, particularly in relation to leadership and formal titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

HasAnnotation

-0.61

osoba

-0.53

owels

-0.52

 PublicKey

-0.52

 Boven

-0.52

 calcu

-0.52

]),

-0.51

 canons

-0.50

Misty

-0.50

PHONY

-0.48

POSITIVE LOGITS

 françaises

0.55

 <=",

0.54

:✨

0.53

Билгалдахарш

0.52

marshaller

0.52

Extinguishing

0.51

 iload

0.50

InstrumentedTest

0.50

DoubleQuotes

0.49

 &___

0.49

Activations Density 0.440%

references to key roles and positions within organizations, particularly in relation to leadership and formal titles

No Comments

No Known Activations