INDEX

Explanations

references to identity or self-referential phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

erunner

-0.63

 hunne

-0.63

astify

-0.61

 дописавши

-0.60

iastes

-0.59

ENOS

-0.57

AppCompatTheme

-0.57

 Racine

-0.56

tdc

-0.56

 brady

-0.55

POSITIVE LOGITS

 itself

1.38

itself

1.34

 Itself

1.29

 Roskov

0.98

 sendiri

0.95

 himself

0.91

 Himself

0.87

本身

0.86

 herself

0.86

themselves

0.84

Activations Density 0.134%

references to identity or self-referential phrases

No Comments

No Known Activations