INDEX

Explanations

indications of cause and effect in statements

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

opus

-0.47

he

-0.44

ssf

-0.44

 Seele

-0.44

ss

-0.43

BeginInit

-0.43

zen

-0.42

 canne

-0.42

ide

-0.41

nos

-0.41

POSITIVE LOGITS

^(@)

0.76

-------------</

0.74

 EconPapers

0.73

 يتيمه

0.73

CloseOperation

0.70

esticular

0.69

RenderAtEndOf

0.67

 Administrativna

0.66

 Савезне

0.66

stretchr

0.66

Activations Density 0.287%

indications of cause and effect in statements

No Comments

No Known Activations