INDEX

Explanations

elements of code snippets or programming syntax

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

"x" followed by digits

np_acts-logits-general · gemini-2.0-flash

x64 plugins

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

messageInfo

-0.55

blurRadius

-0.54

LookAnd

-0.52

andExpect

-0.51

stateProvider

-0.48

detectChanges

-0.48

pushFollow

-0.48

JspWriter

-0.46

 Fury

-0.45

 marry

-0.45

POSITIVE LOGITS

1.47

1.42

1.16

getX

1.10

1.09

setX

1.01

 Xavier

0.96

𝑥

0.96

 getX

0.96

xpress

0.95

Activations Density 0.546%

elements of code snippets or programming syntax

"x" followed by digits

x64 plugins

No Comments

No Known Activations