INDEX

Explanations

questions or statements indicating uncertainty or seeking clarification

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

protoimpl

-0.94



-0.79

تقاوى

-0.78

parsedMessage

-0.75

Especies

-0.65

Personensuche

-0.65

ThroughAttribute

-0.64

 AssemblyTitle

-0.63

 виправивши

-0.62

didSet

-0.59

POSITIVE LOGITS

ποτε

0.48

richTextPanel

0.44

astă

0.42

Cer

0.41

 demurrer

0.41

 seaborn

0.41

 يتيمه

0.41

ächst

0.41

getSupport

0.40

 rzeczy

0.39

Activations Density 0.284%

questions or statements indicating uncertainty or seeking clarification

No Comments

No Known Activations