INDEX

Explanations

specific formatting indicators or markers in code or structured text

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

published notes

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

StructEnd

-0.75

 autorytatywna

-0.60

thâu

-0.57

 كومونز

-0.56

Efq

-0.55

pushFollow

-0.54

 pinulongan

-0.52

($__

-0.52

reactstrap

-0.52

Vidite

-0.52

POSITIVE LOGITS

matchCondition

0.35

Sklici

0.34

 rzeczyw

0.33

mobileqq

0.32

Примечания

0.32

TV

0.32

GoogleApiClient

0.32

 real

0.31

 saisi

0.31

sprechend

0.31

Activations Density 0.000%

specific formatting indicators or markers in code or structured text

published notes

No Comments

No Known Activations