INDEX

Explanations

the presence of the word "Qu" and variations of it, indicating a focus on content related to quantum

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Efq

-2.06

 myſelf

-2.02

 Monfieur

-2.00

 itſelf

-1.95

 pleaſure

-1.89

 Houſe

-1.88

 Reſ

-1.88

 purpoſe

-1.83

 Majefty

-1.83

 ſeveral

-1.81

POSITIVE LOGITS

Qu

1.05

qu

1.05

0.89

0.88

0.87

0.86

0.85

<eos>

0.82

Activations Density 0.177%

the presence of the word "Qu" and variations of it, indicating a focus on content related to quantum

No Comments

No Known Activations