INDEX

Explanations

phrases that emphasize significance or importance

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

 vectorielle

-0.81



-0.81

azgo

-0.78

LookAnd

-0.73

 bonté

-0.73

 spirituale

-0.72

 يتيمه

-0.71

 popolazione

-0.71

oporosis

-0.70

 Rossetti

-0.69

POSITIVE LOGITS

 bigger

1.04

bigger

0.88

 biggest

0.82

 Bigger

0.82

Bigger

0.79

big

0.75

Biggest

0.67

biggest

0.66

 schlimm

0.63

 Biggest

0.62

Activations Density 0.064%

phrases that emphasize significance or importance

No Comments

No Known Activations