INDEX

Explanations

negative sentiment or criticism

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EReference

-0.67

ToScroll

-0.67

ourne

-0.60

︎

-0.60

sams

-0.60

ftime

-0.59

LookAnd

-0.59

rsiniz

-0.59

 useAuth

-0.58

 Moura

-0.57

POSITIVE LOGITS

−

0.62

−

0.58

ing

0.52

kel

0.47

ization

0.45

 Kelley

0.44

 reutiliz

0.44

<h2>

0.43

hintText

0.42

al

0.41

Activations Density 0.064%

negative sentiment or criticism

No Comments

No Known Activations