INDEX

Explanations

terms related to access, rights, and control

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

granted, permission, control

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

]<<"

-0.58

endforeach

-0.50

adí

-0.48

']")

-0.47

:✨

-0.46

iya

-0.46

 Benson

-0.46

 localObject

-0.46

tire

-0.46

Hvis

-0.46

POSITIVE LOGITS

 granted

0.73

MENAFN

0.72

 متعلقه

0.66

 accordé

0.65

 gained

0.64

createObject

0.63

AnchorTagHelper

0.62

 Wikimedijinoj

0.61

adpleegd

0.60

 attained

0.59

Activations Density 0.403%

terms related to access, rights, and control

granted, permission, control

No Comments

No Known Activations