INDEX

Explanations

phrases indicating causation or potential outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

antMatchers

-0.65

 للمعارف

-0.64

ArrowToggle

-0.63

 beginnetje

-0.61

ValueGenerated

-0.58

 AssemblyCompany

-0.57

GeneratedCode

-0.55

 mergeFrom

-0.54

stości

-0.52

 '\\;'

-0.51

POSITIVE LOGITS

 idea

2.08

 notion

1.91

 fact

1.70

idée

1.50

idea

1.48

 concept

1.47

 ideia

1.43

 possibility

1.40

 idée

1.40

 assumption

1.33

Activations Density 0.605%

phrases indicating causation or potential outcomes

No Comments

No Known Activations