INDEX

Explanations

negations or phrases indicating the absence of something

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

 незавершена

-0.77

 hakim

-0.75

bender

-0.73

 dorada

-0.72

 esmeralda

-0.71

httphttps

-0.70

 TableColumn

-0.70

 Appellee

-0.70

 Bremen

-0.69

Herald

-0.69

POSITIVE LOGITS

Not

0.86

Not

0.80

NOT

0.72

 trent

0.70

 quite

0.68

NOT

0.67

ing

0.66

 Notting

0.66

 enggak

0.66

Quite

0.66

Activations Density 0.105%

negations or phrases indicating the absence of something

No Comments

No Known Activations