INDEX

Explanations

questions and statements about identity and self-perception

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

 pleaſure

-0.73

 fevere

-0.69

دانشنامهٔ

-0.67

 fuper

-0.62

 fhort

-0.61

 ―――――

-0.61

 poffible

-0.60

oredCriteria

-0.60

 againſt

-0.60

 neceff

-0.59

POSITIVE LOGITS

pezi

0.55

KURZBESCHREIBUNG

0.55

bodyParser

0.51

artifactId

0.51

 State

0.50

+:+

0.49

gdala

0.48

تقاوى

0.46

\{\\

0.46

lude

0.46

Activations Density 0.218%

questions and statements about identity and self-perception

No Comments

No Known Activations