INDEX

Explanations

sequences that indicate procedural steps or instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

 ddelweddau

-0.81

Efq

-0.73

 FontWeight

-0.61

ſelf

-0.59

 Monfieur

-0.58

 ProtoMessage

-0.58

 Jefus

-0.57

}{@

-0.56

 disambiguazione

-0.54

 juſt

-0.53

POSITIVE LOGITS

 Then

0.80

 Danach

0.75

DockStyle

0.75

 then

0.73

then

0.72

Then

0.70

 Anschließend

0.68

 THEN

0.68

 Thereafter

0.67

帖最后由

0.64

Activations Density 0.383%

sequences that indicate procedural steps or instructions

No Comments

No Known Activations

sequences that indicate procedural steps or instructions

No Comments

No Known Activations