INDEX

Explanations

proper nouns, specifically names of people

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ChildScrollView

-0.60

 BorderRadius

-0.60

 AssemblyProduct

-0.55

MigrationBuilder

-0.55

 figure

-0.53

 pageable

-0.52

AddTagHelper

-0.52

EndProject

-0.51

อย่าง

-0.51

negan

-0.51

POSITIVE LOGITS

 Tapatalk

0.61

ništ

0.59

 domés

0.57

AttributeSet

0.56

 nahilalakip

0.53

 honte

0.52

Slf

0.51

 anledning

0.51

 Questi

0.50

 senare

0.50

Activations Density 0.148%

proper nouns, specifically names of people

No Comments

No Known Activations