INDEX

Explanations

phrases indicating capability or potential actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

DoubleQuotes

-0.76

 Mors

-0.74

 AspNetCore

-0.73

 ***!

-0.71

upsi

-0.70

 dwarfs

-0.70

YSIS

-0.69

רושלים

-0.69

yw

-0.69

bootstrapcdn

-0.68

POSITIVE LOGITS

 able

1.58

 Able

1.46

Able

1.30

 Ability

1.14

 ability

1.11

Ability

1.03

 abilities

1.01

 Unable

0.91

 Abilities

0.88

 unable

0.88

Activations Density 0.058%

phrases indicating capability or potential actions

No Comments

No Known Activations