INDEX

Explanations

proper nouns and locations, particularly related to inventions and notable individuals

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

Autoritní

-0.81

MigrationBuilder

-0.71

RectangleBorder

-0.65

itinéraire

-0.64

hyrchwyd

-0.62

 Gelder

-0.61

IUrlHelper

-0.61

twimg

-0.60

 للاسماء

-0.60

 '\\;'

-0.59

POSITIVE LOGITS

}{@

0.58

Pautan

0.51

نجليزية

0.50

$(\

0.49

 geslacht

0.47

born

0.45

 שוליים

0.44

平民

0.44

'{@

0.44

ElementException

0.43

Activations Density 0.316%

proper nouns and locations, particularly related to inventions and notable individuals

No Comments

No Known Activations