INDEX

Explanations

phrases related to actions and dynamics involving positions or directions in a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

enis

-0.54

She

-0.53

erty

-0.47

niająca

-0.47

ApiModelProperty

-0.47

ито

-0.46

izumi

-0.45

oval

-0.44

estimm

-0.43

Can

-0.42

POSITIVE LOGITS

 فريبيس

1.06

󠁢

0.80

 InputDecoration

0.80



0.78

 AssemblyVersion

0.71

 שוליים

0.70

SOUNDBITE

0.69

 estekak

0.68

Geplaatst

0.67

initializeApp

0.66

Activations Density 0.565%

phrases related to actions and dynamics involving positions or directions in a context

No Comments

No Known Activations