INDEX

Explanations

phrases indicating a range or comparison, particularly those that involve the word "between"

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

 RSSSF

-0.72

 sandero

-0.71

erweise

-0.71

 Folly

-0.69

 Sandi

-0.69

 AppColors

-0.65

 vectorielles

-0.65

 complètes

-0.64

 Mace

-0.64

 Tacitus

-0.63

POSITIVE LOGITS

between

1.69

 Between

1.64

 between

1.62

BETWEEN

1.62

Between

1.59

 BETWEEN

1.58

 zwischen

1.40

 tussen

1.36

 betwixt

1.34

 entre

1.31

Activations Density 0.105%

phrases indicating a range or comparison, particularly those that involve the word "between"

No Comments

No Known Activations