INDEX

Explanations

the word "Plus" and variations of it in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

entery

-0.72

 Dene

-0.72

 Sark

-0.72

posób

-0.71

 initComponents

-0.69

JAL

-0.68

thschild

-0.66

'},

-0.64

fileID

-0.64

Becker

-0.64

POSITIVE LOGITS

 PLUS

1.48

plus

1.46

 plus

1.43

PLUS

1.39

Plus

1.38

 Plus

1.34

 Minus

1.15

Minus

1.09

mybatisplus

1.07

minus

1.04

Activations Density 0.077%

the word "Plus" and variations of it in different contexts

No Comments

No Known Activations