INDEX

Explanations

instances of the word "me" and variations related to self-reference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

SourceChecksum

-0.75

новниш

-0.73

 متعلقه

-0.73

oneofs

-0.58

uscht

-0.57

 مرئيه

-0.57

 beginnetje

-0.55

Geplaatst

-0.54

ünstig

-0.54

UnknownFieldSet

-0.54

POSITIVE LOGITS

 even

2.27

even

2.10

Even

1.87

 EVEN

1.83

 Even

1.79

EVEN

1.72

 persino

1.62

 навіть

1.60

Даже

1.56

 incluso

1.54

Activations Density 0.262%

instances of the word "me" and variations related to self-reference

No Comments

No Known Activations