INDEX

Explanations

questions that seek clarification or challenge assumptions

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

Follows conjunctions/relative pronouns

np_acts-logits-general · gemini-2.0-flash

actions after clauses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

AndEndTag

-0.69

 використову

-0.67

 calendriers

-0.62

UserScript

-0.56

bbene

-0.55

 المعيارى

-0.54

Према

-0.52

 Далее

-0.49

 iconFacebook

-0.47

tende

-0.47

POSITIVE LOGITS

 having

1.46

 getting

1.39

having

1.25

 putting

1.24

 taking

1.23

 adding

1.23

 doing

1.21

 making

1.18

 keeping

1.17

 finding

1.14

Activations Density 1.025%

questions that seek clarification or challenge assumptions

Follows conjunctions/relative pronouns

actions after clauses

No Comments

No Known Activations