INDEX

Explanations

references to programming structures and operations in code snippets

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

Code involving appending or adding

np_acts-logits-general · gemini-2.0-flash

adding to lists

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

SourceChecksum

-0.57

ContextHolder

-0.52

UALA

-0.51

eleste

-0.49

ViewFeatures

-0.48

 оригіналу

-0.48

ształ

-0.48

 genie

-0.47

 Ause

-0.46

ilim

-0.46

POSITIVE LOGITS

add

2.42

 adding

2.28

 added

2.19

Add

2.18

 addition

2.17

 Adding

2.09

add

2.09

 Addition

2.06

 adds

2.04

Add

2.04

Activations Density 0.571%

references to programming structures and operations in code snippets

Code involving appending or adding

adding to lists

No Comments

No Known Activations