INDEX

Explanations

phrases that indicate the presence of "there" statements or existential conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

----</

-0.65

Erreferentziak

-0.64

MarshalTo

-0.58

 kaarangay

-0.57

WebVitals

-0.56

GeneratedValue

-0.54

 unknownFields

-0.53

createServer

-0.52

ništvo

-0.50

ItemBackground

-0.49

POSITIVE LOGITS

 there

3.44

there

2.74

 There

2.59

There

2.51

 THERE

2.45

THERE

2.11

 هناك

1.84

 theres

1.71

theres

1.65

Theres

1.45

Activations Density 0.649%

phrases that indicate the presence of "there" statements or existential conditions

No Comments

No Known Activations