INDEX

Explanations

phrases that indicate suggestions, recommendations, or guidelines directed at the reader

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

']],

-0.53

İŞ

-0.49

Bảo

-0.46

']))

-0.45

UseVisualStyle

-0.45

"])

-0.44

 memberId

-0.43

pers

-0.43

-0.42

CrossRef

-0.42

POSITIVE LOGITS

 want

1.20

want

0.93

 querr

0.90

 wanna

0.88

 wants

0.88

 wanting

0.83

 WANT

0.78

 Want

0.78

Want

0.73

 devriez

0.73

Activations Density 0.138%

phrases that indicate suggestions, recommendations, or guidelines directed at the reader

No Comments

No Known Activations