INDEX

Explanations

statements and actions that indicate criticism or defense regarding controversial topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 Aufs

-0.48

 leaſt

-0.48

Batis

-0.46

ColumnHeader

-0.45

 Infect

-0.45

 littéraire

-0.45

 Barrel

-0.45

oldest

-0.43

 decorativa

-0.43

 lille

-0.43

POSITIVE LOGITS

Personendaten

1.11

SourceChecksum

0.93

ValueStyle

0.90

 propOrder

0.89

 nahilalakip

0.82

windowFixed

0.76

ArrowToggle

0.75

 autorytatywna

0.73

parsedMessage

0.67

 disambiguazione

0.67

Activations Density 0.303%

statements and actions that indicate criticism or defense regarding controversial topics

No Comments

No Known Activations