INDEX

Explanations

phrases indicating the existence or quantity of various elements or conditions

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

 verksamhet

-0.64

Everything

-0.56

one

-0.55

tamanya

-0.54

this

-0.54

 aktivitet

-0.54

 Everything

-0.52

zieży

-0.51

This

-0.49

éril

-0.49

POSITIVE LOGITS

few

0.99

 fewer

0.88

 many

0.87

two

0.85

 several

0.83

 times

0.81

few

0.79

 numerous

0.78

 differences

0.76

 some

0.75

Activations Density 0.113%

phrases indicating the existence or quantity of various elements or conditions

No Comments

No Known Activations