INDEX

Explanations

mentions of prominent individuals, particularly in political contexts

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

names, citations, beneficiaries

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

Grove

-0.50

 Grove

-0.47

EReference

-0.46

 endIndex

-0.46

 alatt

-0.44

Burg

-0.44

 getInfo

-0.44

 resultList

-0.44

 encima

-0.44

importanza

-0.44

POSITIVE LOGITS

Zeneca

0.68

 Shaksp

0.60

➯

0.56

ered

0.55

Chas

0.53

adecimal

0.52

racha

0.52

 Solano

0.51

 Zhao

0.50

<!--[

0.50

Activations Density 0.026%

mentions of prominent individuals, particularly in political contexts

names, citations, beneficiaries

No Comments

No Known Activations