INDEX

Explanations

references to valleys, particularly with variations in capitalization

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 disambiguazione

-0.65

 stol

-0.62

الإنجليزية

-0.60

 AssemblyCulture

-0.55

 agre

-0.54

 promet

-0.54

 Promenade

-0.53

 Marlin

-0.53

onedDateTime

-0.53

 opérateur

-0.52

POSITIVE LOGITS

 Valley

2.20

 VALLEY

2.08

 valley

2.03

Valley

1.94

valley

1.84

 valleys

1.35

 vallée

1.34

 valle

0.95

 Valle

0.89

valle

0.80

Activations Density 0.095%

references to valleys, particularly with variations in capitalization

No Comments

No Known Activations