INDEX

Explanations

expressions related to inconsistencies and formality in communication

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

 propOrder

-0.67

 Establishment

-0.61

pires

-0.59

Préparation

-0.58

ickers

-0.58

Só

-0.55

 ArrayAdapter

-0.54

(;;)

-0.53

Arrangements

-0.53

extAlignment

-0.53

POSITIVE LOGITS

RectangleBorder

0.66

 cautious

0.59

UnsafeEnabled

0.55

 careful

0.53

fromnode

0.52

awaiter

0.50

 picky

0.50

thalten

0.49

󠁣

0.49

 proactive

0.47

Activations Density 0.174%

expressions related to inconsistencies and formality in communication

No Comments

No Known Activations