INDEX

Explanations

instances of the word "similar."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 vedno

-0.56

 AsyncTask

-0.56

FXML

-0.55

ništvo

-0.54

cassert

-0.53

stdc

-0.52

都不是

-0.51

äiv

-0.51

PCell

-0.50

PONENT

-0.48

POSITIVE LOGITS

 similar

3.77

similar

3.60

Similar

3.48

 Similar

3.35

 SIMILAR

3.20

 similaire

2.82

 similares

2.73

 semelhante

2.50

 comparable

2.47

 similaires

2.46

Activations Density 0.084%

instances of the word "similar."

No Comments

No Known Activations