INDEX

Explanations

quantifiable descriptions of entities and their characteristics

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

 AssemblyCulture

-1.11

Personendaten

-0.92

 kaarangay

-0.81

AndEndTag

-0.78

 متعلقه

-0.72

SuppressLint

-0.72

 gyhoeddwyd

-0.70

JspWriter

-0.69

 mergeFrom

-0.68

 nahilalakip

-0.68

POSITIVE LOGITS

 sites

0.57

 locations

0.55

 facilities

0.54

แห่ง

0.54

 buildings

0.53

 parks

0.51

 site

0.51

 located

0.49

 town

0.48

 district

0.48

Activations Density 0.535%

quantifiable descriptions of entities and their characteristics

No Comments

No Known Activations