INDEX

Explanations

references to vague or undefined concepts

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

TagMode

-0.79

日閲覧

-0.73

зоры

-0.70

TMS

-0.70

owohl

-0.69

Datuak

-0.69

 isles

-0.68

mejores

-0.67

efois

-0.66

prefixer

-0.65

POSITIVE LOGITS

 something

1.60

Something

1.57

something

1.55

 Something

1.53

 SOMETHING

1.42

ETHING

1.42

 somethin

1.22

 else

1.18

Somebody

1.13

 somebody

1.12

Activations Density 0.096%

references to vague or undefined concepts

No Comments

No Known Activations