INDEX

Explanations

phrases or terms that indicate a sequential action or event

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 Jefus

-1.01

 Theſe

-1.00

Efq

-0.94

 Monfieur

-0.93

 myſelf

-0.91

 himſelf

-0.90

 itſelf

-0.88

 Diſ

-0.87

 purpoſe

-0.82

 AttributeSet

-0.82

POSITIVE LOGITS

 after

1.82

after

1.69

 After

1.59

After

1.56

 после

1.47

 après

1.42

 dopo

1.42

AFTER

1.41

 após

1.38

 AFTER

1.37

Activations Density 0.300%

phrases or terms that indicate a sequential action or event

No Comments

No Known Activations

phrases or terms that indicate a sequential action or event

No Comments

No Known Activations