INDEX

Explanations

proper nouns, specifically names of people

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

names of people

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

 comprobar

-0.42

 siihen

-0.42

 erfaring

-0.40

oost

-0.40

aroos

-0.39

לְ

-0.39

 rzeczy

-0.39

ptăm

-0.39

cryption

-0.38

 protegido

-0.38

POSITIVE LOGITS

AndEndTag

0.49

!*\

0.49

WithIOException

0.47

CppMethod

0.46

RuleContext

0.45

 հղումներ

0.45

RTEX

0.43

writeFieldEnd

0.41

########.

0.40

NameInMap

0.40

Activations Density 0.027%

proper nouns, specifically names of people

names of people

No Comments

No Known Activations