INDEX

Explanations

phrases and questions focused on data collection and evaluation

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

Following "what" or "that"

np_acts-logits-general · gemini-2.0-flash

what we want to know

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

Insee

-0.57

also

-0.56

也很

-0.56

Очень

-0.54

Very

-0.53

very

-0.51

Final

-0.49

 belirt

-0.49

也非常

-0.48

AddField

-0.48

POSITIVE LOGITS

 realmente

0.71

 best

0.70

 verdaderamente

0.68

 efectivamente

0.68

 المعيارى

0.68

บ้าง

0.68

RetentionPolicy

0.68

resizingMask

0.67

 snippetHide

0.66

 really

0.65

Activations Density 0.308%

phrases and questions focused on data collection and evaluation

Following "what" or "that"

what we want to know

No Comments

No Known Activations