INDEX

Explanations

phrases indicating frequency or routine actions

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

Preceding words before a conditional statement

np_acts-logits-general · gemini-2.0-flash

finding differences and deviations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 ProtoMessage

-0.72

JoinTable

-0.67

FormTagHelper

-0.66

 AssemblyProduct

-0.63

JspWriter

-0.62

jooq

-0.60

 resourceCulture

-0.60

ViewFeatures

-0.60

 ferons

-0.59

 NSCoder

-0.59

POSITIVE LOGITS

 different

0.66

 Different

0.59

 versus

0.58

ختلف

0.57

 глазами

0.57

Different

0.56

".

0.55

 challenges

0.55

 pitfalls

0.55

 trends

0.55

Activations Density 0.376%

phrases indicating frequency or routine actions

Preceding words before a conditional statement

finding differences and deviations

No Comments

No Known Activations