INDEX

Explanations

conjunctions and phrases indicating connections or relationships between ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

DeleteBehavior

-0.71

 tranſ

-0.71

 CreateTagHelper

-0.66

parsedMessage

-0.66

 chofe

-0.66

 whoſe

-0.64

 resourceCulture

-0.64

 deſt

-0.63

 himſelf

-0.63

 poffe

-0.62

POSITIVE LOGITS

 whatnot

2.13

etc

1.97

etc

1.65

 stuff

1.64

 whatever

1.52

 such

1.49

Etc

1.46

 sebagainya

1.46

Etc

1.42

 everything

1.39

Activations Density 0.270%

conjunctions and phrases indicating connections or relationships between ideas

No Comments

No Known Activations