INDEX

Explanations

phrases that discuss the significance or characteristics of different subjects

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

Follows "about"

np_acts-logits-general · gemini-2.0-flash

the thing about

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Pelop

-0.76

Efq

-0.72

 Majefty

-0.72

 Ophelia

-0.70

 '\\;'

-0.68

 Shaksp

-0.67

 Fife

-0.66

 Moors

-0.66

 Nagasaki

-0.66

 Euphrates

-0.65

POSITIVE LOGITS

the

0.71

 these

0.66

 this

0.64

it

0.61

Források

0.59

 having

0.58

 owning

0.53

our

0.53

 life

0.50

жи

0.50

Activations Density 0.210%

phrases that discuss the significance or characteristics of different subjects

Follows "about"

the thing about

No Comments

No Known Activations