INDEX

Explanations

expressions of hope and helpfulness

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

Indicates helpfulness or providing assistance

np_acts-logits-general · gemini-2.0-flash

hope that helps

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

########.

-0.50

ngrx

-0.48

">//

-0.47

 calling

-0.46

isRequired

-0.45

 CreateTagHelper

-0.45

 calls

-0.44

inquirer

-0.43

me

-0.43

]=>

-0.43

POSITIVE LOGITS

 snippetHide

0.83

PerformLayout

0.80

 clarify

0.70

chaub

0.69

EOUS

0.69

 ExecuteAsync

0.67

RectangleBorder

0.66

 Clears

0.66

ξύ

0.62

 clarifies

0.62

Activations Density 0.111%

expressions of hope and helpfulness

Indicates helpfulness or providing assistance

hope that helps

No Comments

No Known Activations