INDEX

Explanations

terms related to products, reviews, and university evaluations

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

Mentions or depictions

np_acts-logits-general · gemini-2.0-flash

described or documented content

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

lapsingToolbar

-0.63

unehmen

-0.54

MIDDLEWARE

-0.53

BindingResult

-0.49

:+:

-0.48

andte

-0.48

ingdon

-0.48

OnInit

-0.48

ruptedException

-0.47

 unexplo

-0.47

POSITIVE LOGITS

 mentioned

1.60

 depicted

1.59

 described

1.54

 listed

1.51

 portrayed

1.38

 featured

1.31

 Mentioned

1.28

mentioned

1.26

 shown

1.23

 Described

1.21

Activations Density 0.803%

terms related to products, reviews, and university evaluations

Mentions or depictions

described or documented content

No Comments

No Known Activations