INDEX

Explanations

references to dates and years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 provenance

-0.50

']))

-0.50

 GeoNames

-0.49

displayquote

-0.49

ple

-0.49

レーター

-0.48

 ModelExpression

-0.48

testify

-0.48

defineProperty

-0.47

 avven

-0.47

POSITIVE LOGITS

neſs

0.76

 Chriftian

0.75

tagHelperRunner

0.74

 myſelf

0.69

 Majefty

0.68

 Jefus

0.68

 itſelf

0.67

ſelves

0.67

 reaſon

0.66

 reafon

0.65

Activations Density 0.120%

references to dates and years

No Comments

No Known Activations