INDEX

Explanations

terms related to retirement or individuals who are retired

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

retired status

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

NameInMap

-0.64

 resourceCulture

-0.61

 الحره

-0.52

 BoxFit

-0.51

RuleContext

-0.50

 spørs

-0.50

 <=",

-0.50

IconModule

-0.50

ckså

-0.49

ativement

-0.49

POSITIVE LOGITS

 retired

0.82

retired

0.67

 Retired

0.66

Retired

0.66

 former

0.65

 retirees

0.59

 retiring

0.58

 retire

0.56

 retirement

0.54

 Retire

0.50

Activations Density 0.008%

terms related to retirement or individuals who are retired

retired status

No Comments

No Known Activations