INDEX

Explanations

negations and words indicating uncertainty or denial

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

'},

-0.63

'],

-0.57

ATURE

-0.57

-0.56

NOPQRST

-0.55

lides

-0.54

 onPage

-0.54

lious

-0.54

 niên

-0.53

CGContext

-0.53

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.67

 Exactos

0.63

 disponibilités

0.62

 kaarangay

0.61

 Baillargeon

0.58

LookAnd

0.58

 '\\;'

0.57

回目

0.57

 Biôgrafia

0.57

harusnya

0.55

Activations Density 0.503%

negations and words indicating uncertainty or denial

No Comments

No Known Activations