INDEX

Explanations

phrases indicating similarity or equivalence between concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

randomUUID

-0.55

期刊论文

-0.46

一面

-0.45

cơ

-0.45

ForResult

-0.45

 produisons

-0.44

gnac

-0.44

brtc

-0.44

zelle

-0.44

 body

-0.43

POSITIVE LOGITS

Likewise

0.93

Ditto

0.92

 Likewise

0.89

 ditto

0.85

 likewise

0.85

 Ditto

0.84

 Ebenso

0.83

 viceversa

0.83

Similarly

0.82

 Similarly

0.79

Activations Density 0.223%

phrases indicating similarity or equivalence between concepts

No Comments

No Known Activations