INDEX

Explanations

variations of the word "met," particularly in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

참고

-0.65

WithFormat

-0.61

ProcessEvent

-0.57

 MainAxisSize

-0.56

innung

-0.53

 diferen

-0.53

 mahd

-0.52

 Dokter

-0.51

произ

-0.51

 Brink

-0.51

POSITIVE LOGITS

Met

3.21

Met

3.08

met

2.85

met

2.60

MET

2.41

MET

2.05

 Metcalf

1.58

 Metropolitan

1.49

mets

1.44

 Metz

1.41

Activations Density 0.061%

variations of the word "met," particularly in different contexts

No Comments

No Known Activations