INDEX

Explanations

instances of strong negative emotions or harsh language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

)|^{

-0.69

GIP

-0.63

abestanden

-0.61

—

-0.61

eradish

-0.61

 &___

-0.59

 Sanger

-0.59

зульта

-0.59

 snippetHide

-0.58

 quí

-0.58

POSITIVE LOGITS

ine

0.74

SourceChecksum

0.66

 ویکی‌پدی

0.64

boarding

0.57

master

0.55

 quedarse

0.55

baga

0.54

 belast

0.54

+#+#

0.54

mm

0.53

Activations Density 0.068%

instances of strong negative emotions or harsh language

No Comments

No Known Activations